performance-engineer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Performance Engineer

性能工程师

Specialist in analyzing and optimizing application performance, identifying bottlenecks, and implementing efficiency improvements.

专注于分析和优化应用性能、识别瓶颈并实施效率提升方案的专家。

When This Skill Activates

技能触发场景

Activates when you:

Report performance issues
Need performance optimization
Mention "slow" or "latency"
Want to improve efficiency

在你执行以下操作时触发：

反馈性能问题
需要进行性能优化
提到「慢」或「延迟」相关内容
想要提升效率

Performance Analysis Process

性能分析流程

Phase 1: Identify the Problem

阶段1：定位问题

Define metrics
- What's the baseline?
- What's the target?
- What's acceptable?

Measure current performance

bash

# Response time
curl -w "@curl-format.txt" -o /dev/null -s https://example.com/users

# Database query time
# Add timing logs to queries

# Memory usage
# Use profiler

Profile the application

bash

# Node.js
node --prof app.js

# Python
python -m cProfile app.py

# Go
go test -cpuprofile=cpu.prof

定义指标
- 基准值是多少？
- 优化目标是多少？
- 可接受的阈值是多少？

测量当前性能

bash

# 响应时间
curl -w "@curl-format.txt" -o /dev/null -s https://example.com/users

# 数据库查询耗时
# 给查询添加计时日志

# 内存使用情况
# 使用性能剖析工具

对应用做性能剖析

bash

# Node.js
node --prof app.js

# Python
python -m cProfile app.py

# Go
go test -cpuprofile=cpu.prof

Phase 2: Find the Bottleneck

阶段2：查找瓶颈

Common bottleneck locations:

Layer	Common Issues
Database	N+1 queries, missing indexes, large result sets
API	Over-fetching, no caching, serial requests
Application	Inefficient algorithms, excessive logging
Frontend	Large bundles, re-renders, no lazy loading
Network	Too many requests, large payloads, no compression

常见瓶颈位置：

层级	常见问题
数据库	N+1 查询、索引缺失、结果集过大
API	过度拉取、无缓存、串行请求
应用层	算法效率低、日志输出过多
前端	包体积过大、不必要重渲染、未使用懒加载
网络	请求次数过多、 payload 过大、未开启压缩

Phase 3: Optimize

阶段3：优化

Database Optimization

数据库优化

N+1 Queries:

typescript

// Bad: N+1 queries
const users = await User.findAll();
for (const user of users) {
  user.posts = await Post.findAll({ where: { userId: user.id } });
}

// Good: Eager loading
const users = await User.findAll({
  include: [{ model: Post, as: 'posts' }]
});

Missing Indexes:

sql

-- Add index on frequently queried columns
CREATE INDEX idx_user_email ON users(email);
CREATE INDEX idx_post_user_id ON posts(user_id);

N+1 查询：

typescript

// Bad: N+1 queries
const users = await User.findAll();
for (const user of users) {
  user.posts = await Post.findAll({ where: { userId: user.id } });
}

// Good: Eager loading
const users = await User.findAll({
  include: [{ model: Post, as: 'posts' }]
});

索引缺失：

sql

-- 给高频查询的字段添加索引
CREATE INDEX idx_user_email ON users(email);
CREATE INDEX idx_post_user_id ON posts(user_id);

API Optimization

API 优化

Pagination:

typescript

// Always paginate large result sets
const users = await User.findAll({
  limit: 100,
  offset: page * 100
});

Field Selection:

typescript

// Select only needed fields
const users = await User.findAll({
  attributes: ['id', 'name', 'email']
});

Compression:

typescript

// Enable gzip compression
app.use(compression());

分页：

typescript

// 大结果集必须做分页
const users = await User.findAll({
  limit: 100,
  offset: page * 100
});

字段裁剪：

typescript

// 仅选择需要的字段
const users = await User.findAll({
  attributes: ['id', 'name', 'email']
});

压缩：

typescript

// 开启gzip压缩
app.use(compression());

Frontend Optimization

前端优化

Code Splitting:

typescript

// Lazy load routes
const Dashboard = lazy(() => import('./Dashboard'));

Memoization:

typescript

// Use useMemo for expensive calculations
const filtered = useMemo(() =>
  items.filter(item => item.active),
  [items]
);

Image Optimization:

Use WebP format
Lazy load images
Use responsive images
Compress images

代码分割：

typescript

// 路由懒加载
const Dashboard = lazy(() => import('./Dashboard'));

记忆化缓存：

typescript

// 高开销计算使用useMemo缓存
const filtered = useMemo(() =>
  items.filter(item => item.active),
  [items]
);

图片优化：

使用WebP格式
图片懒加载
使用响应式图片
压缩图片体积

Phase 4: Verify

阶段4：验证

Measure again
Compare to baseline
Ensure no regressions
Document the improvement

再次测量性能
和基准值做对比
确保没有引入功能回归
记录优化效果

Performance Targets

性能指标目标

Metric	Target	Critical Threshold
API Response (p50)	< 100ms	< 500ms
API Response (p95)	< 500ms	< 1s
API Response (p99)	< 1s	< 2s
Database Query	< 50ms	< 200ms
Page Load (FMP)	< 2s	< 3s
Time to Interactive	< 3s	< 5s
Memory Usage	< 512MB	< 1GB

指标	目标值	临界阈值
API响应 (p50)	< 100ms	< 500ms
API响应 (p95)	< 500ms	< 1s
API响应 (p99)	< 1s	< 2s
数据库查询	< 50ms	< 200ms
页面加载 (FMP)	< 2s	< 3s
可交互时间	< 3s	< 5s
内存使用	< 512MB	< 1GB

Common Optimizations

常见优化手段

Caching Strategy

缓存策略

typescript

// Cache expensive computations
const cache = new Map();

async function getUserStats(userId: string) {
  if (cache.has(userId)) {
    return cache.get(userId);
  }

  const stats = await calculateUserStats(userId);
  cache.set(userId, stats);

  // Invalidate after 5 minutes
  setTimeout(() => cache.delete(userId), 5 * 60 * 1000);

  return stats;
}

typescript

// 缓存高开销计算结果
const cache = new Map();

async function getUserStats(userId: string) {
  if (cache.has(userId)) {
    return cache.get(userId);
  }

  const stats = await calculateUserStats(userId);
  cache.set(userId, stats);

  // 5分钟后失效
  setTimeout(() => cache.delete(userId), 5 * 60 * 1000);

  return stats;
}

Batch Processing

批量处理

typescript

// Bad: Individual requests
for (const id of userIds) {
  await fetchUser(id);
}

// Good: Batch request
await fetchUsers(userIds);

typescript

// Bad: 单次请求逐个查询
for (const id of userIds) {
  await fetchUser(id);
}

// Good: 批量请求
await fetchUsers(userIds);

Debouncing/Throttling

防抖/节流

typescript

// Debounce search input
const debouncedSearch = debounce(search, 300);

// Throttle scroll events
const throttledScroll = throttle(handleScroll, 100);

typescript

// 搜索输入防抖
const debouncedSearch = debounce(search, 300);

// 滚动事件节流
const throttledScroll = throttle(handleScroll, 100);

Performance Monitoring

性能监控

Key Metrics

核心指标

Response Time: Time to process request
Throughput: Requests per second
Error Rate: Failed requests percentage
Memory Usage: Heap/RAM used
CPU Usage: Processor utilization

响应时间：处理请求的耗时
吞吐量：每秒处理的请求数
错误率：请求失败的占比
内存使用：堆/内存占用量
CPU使用率：处理器利用率

Monitoring Tools

监控工具

Tool	Purpose
Lighthouse	Frontend performance
New Relic	APM monitoring
Datadog	Infrastructure monitoring
Prometheus	Metrics collection

工具	用途
Lighthouse	前端性能检测
New Relic	APM性能监控
Datadog	基础设施监控
Prometheus	指标采集

Scripts

脚本

Profile application:

bash

python scripts/profile.py

Generate performance report:

bash

python scripts/perf_report.py

应用性能剖析：

bash

python scripts/profile.py

生成性能报告：

bash

python scripts/perf_report.py

References

参考资料

```
references/optimization.md
```
- Optimization techniques
```
references/monitoring.md
```
- Monitoring setup
```
references/checklist.md
```
- Performance checklist

```
references/optimization.md
```
- 优化技巧
```
references/monitoring.md
```
- 监控配置
```
references/checklist.md
```
- 性能检查清单