Actuator 与可观测性接入

management:
  endpoints:
    web:
      exposure:
        include: health
  endpoint:
    health:
      # 显示详细健康信息
      show-details: when_authorized  # never | always | when_authorized
      # 显示组件详细信息
      show-components: when_authorized
      # 探针配置
      probes:
        enabled: true

{
  "status": "UP",
  "components": {
    "db": {
      "status": "UP",
      "details": {
        "database": "MySQL",
        "validationQuery": "isValid()"
      }
    },
    "redis": {
      "status": "UP",
      "details": {
        "version": "7.0.0"
      }
    },
    "diskSpace": {
      "status": "UP",
      "details": {
        "total": 107374182400,
        "free": 53687091200,
        "threshold": 10485760
      }
    }
  }
}

@Component
public class CustomHealthIndicator implements HealthIndicator {
    
    @Autowired
    private ExternalServiceClient externalServiceClient;
    
    @Override
    public Health health() {
        // 检查外部服务
        try {
            if (externalServiceClient.isAvailable()) {
                return Health.up()
                    .withDetail("externalService", "available")
                    .build();
            } else {
                return Health.down()
                    .withDetail("externalService", "unavailable")
                    .build();
            }
        } catch (Exception e) {
            return Health.down()
                .withDetail("error", e.getMessage())
                .build();
        }
}

{
  "status": "UP",
  "components": {
    "customHealth": {
      "status": "UP",
      "details": {
        "externalService": "available"
      }
    }
  }
}

@Component
public class CompositeHealthIndicator implements HealthIndicator {
    
    @Autowired
    private List<HealthIndicator> indicators;
    
    @Override
    public Health health() {
        List<Health> healths = indicators.stream()
            .map(HealthIndicator::health)
            .collect(Collectors.toList());
        
        // 所有组件都健康才算健康
        boolean allUp = healths.stream()
            .allMatch(h -> h.getStatus() == Status.UP);
        
        if (allUp) {
            return Health.up()
                .withDetail("components", healths.size())
                .build();
        } else {
            return Health.down()
                .withDetail("components", healths)
                .build();
        }
    }
}

management:
  endpoint:
    health:
      probes:
        enabled: true

// 自定义存活探针
@Component
public class LivenessHealthIndicator implements HealthIndicator {
    
    @Override
    public Health health() {
        // 检查关键资源是否正常
        // 如:数据库连接池是否耗尽
        return Health.up().build();
    }
}

// 自定义就绪探针
@Component
public class ReadinessHealthIndicator implements HealthIndicator {
    
    @Override
    public Health health() {
        // 检查是否准备好接收流量
        // 如:预热是否完成、依赖服务是否可用
        return Health.up().build();
    }
}

# Kubernetes Deployment配置
apiVersion: apps/v1
kind: Deployment
metadata:
  name: myapp
spec:
  template:
    spec:
      containers:
      - name: myapp
        image: myapp:latest
        livenessProbe:
          httpGet:
            path: /actuator/health/liveness
            port: 8080
          initialDelaySeconds: 30
          periodSeconds: 10
        readinessProbe:
          httpGet:
            path: /actuator/health/readiness
            port: 8080
          initialDelaySeconds: 10
          periodSeconds: 5

management:
  info:
    env:
      enabled: true
    git:
      mode: full
    build:
      enabled: true

info:
  app:
    name: My Application
    description: Spring Boot Application
    version: 1.0.0
  author:
    name: John Doe
    email: john@example.com

{
  "app": {
    "name": "My Application",
    "description": "Spring Boot Application",
    "version": "1.0.0"
  },
  "author": {
    "name": "John Doe",
    "email": "john@example.com"
  },
  "git": {
    "branch": "main",
    "commit": {
      "id": "abc123",
      "time": "2024-03-30T10:00:00Z"
    }
  },
  "build": {
    "artifact": "my-app",
    "name": "My App",
    "time": "2024-03-30T09:00:00Z",
    "version": "1.0.0",
    "group": "com.example"
  }
}

@Component
public class CustomInfoContributor implements InfoContributor {
    
    @Autowired
    private BuildProperties buildProperties;
    
    @Override
    public void contribute(Info.Builder builder) {
        builder.withDetail("custom", 
            Map.of(
                "javaVersion", System.getProperty("java.version"),
                "osName", System.getProperty("os.name"),
                "buildTime", buildProperties.getTime(),
                "buildVersion", buildProperties.getVersion()
            )
        );
    }
}

GET /actuator/metrics

{
  "names": [
    "jvm.memory.used",
    "jvm.memory.max",
    "jvm.gc.pause",
    "process.cpu.usage",
    "http.server.requests",
    "hikaricp.connections.active",
    "hikaricp.connections.pending"
  ]
}

GET /actuator/metrics/jvm.memory.used

{
  "name": "jvm.memory.used",
  "description": "The amount of used memory",
  "baseUnit": "bytes",
  "measurements": [
    {
      "statistic": "VALUE",
      "value": 1.23456789E8
    }
  ],
  "availableTags": [
    {
      "tag": "area",
      "values": ["heap", "nonheap"]
    },
    {
      "tag": "id",
      "values": ["G1 Survivor Space", "G1 Old Gen", "G1 Eden Space"]
    }
  ]
}

GET /actuator/metrics/jvm.memory.used?tag=area:heap

{
  "name": "jvm.memory.used",
  "measurements": [
    {
      "statistic": "VALUE",
      "value": 8.7654321E7
    }
  ]
}

<dependency>
    <groupId>io.micrometer</groupId>
    <artifactId>micrometer-registry-prometheus</artifactId>
</dependency>

management:
  endpoints:
    web:
      exposure:
        include: prometheus
  prometheus:
    metrics:
      export:
        enabled: true

GET /actuator/prometheus

# HELP jvm_memory_used_bytes The amount of used memory
# TYPE jvm_memory_used_bytes gauge
jvm_memory_used_bytes{area="heap",id="G1 Old Gen",} 1.23456789E8
jvm_memory_used_bytes{area="heap",id="G1 Eden Space",} 2.3456789E7

# HELP http_server_requests_seconds  
# TYPE http_server_requests_seconds summary
http_server_requests_seconds_count{exception="None",method="GET",outcome="SUCCESS",status="200",uri="/api/users",} 100.0
http_server_requests_seconds_sum{exception="None",method="GET",outcome="SUCCESS",status="200",uri="/api/users",} 1.234

GET /actuator/env

{
  "activeProfiles": ["dev"],
  "propertySources": [
    {
      "name": "application.yml",
      "properties": {
        "server.port": {
          "value": "8080",
          "origin": "class path resource [application.yml]:2:13"
        }
      }
    }
  ]
}

GET /actuator/env/server.port

{
  "property": {
    "value": "8080",
    "origin": "class path resource [application.yml]:2:13"
  },
  "activeProfiles": ["dev"],
  "propertySources": [...]
}

management:
  endpoint:
    env:
      enabled: false  # 禁用env端点
      
# 或使用Spring Security限制访问
management:
  endpoint:
    env:
      show-values: never  # 不显示值

GET /actuator/loggers

{
  "levels": ["OFF", "ERROR", "WARN", "INFO", "DEBUG", "TRACE"],
  "loggers": {
    "ROOT": {
      "configuredLevel": "INFO",
      "effectiveLevel": "INFO"
    },
    "com.example": {
      "configuredLevel": "DEBUG",
      "effectiveLevel": "DEBUG"
    }
  }
}

GET /actuator/loggers/com.example

{
  "configuredLevel": "DEBUG",
  "effectiveLevel": "DEBUG"
}

POST /actuator/loggers/com.example
Content-Type: application/json

{
  "configuredLevel": "TRACE"
}

# 生产环境临时开启 DEBUG 排查问题
curl -X POST http://localhost:8081/actuator/loggers/com.example \
     -H 'Content-Type: application/json' \
     -d '{"configuredLevel": "DEBUG"}'

GET /actuator/threaddump

[
  {
    "threadName": "main",
    "threadState": "RUNNABLE",
    "priority": 5,
    "stackTrace": [...]
  },
  {
    "threadName": "http-nio-8080-exec-1",
    "threadState": "WAITING",
    "priority": 5,
    "stackTrace": [...]
  }
]

GET /actuator/heapdump

# 返回二进制文件,可用jvisualvm或MAT分析

management:
  endpoint:
    heapdump:
      enabled: false  # 生产环境建议禁用

<dependency>
    <groupId>io.micrometer</groupId>
    <artifactId>micrometer-core</artifactId>
</dependency>

@Service
public class OrderService {
    
    private final Counter orderCounter;
    
    public OrderService(MeterRegistry meterRegistry) {
        this.orderCounter = Counter.builder("orders.created")
            .description("Total orders created")
            .tag("type", "normal")
            .register(meterRegistry);
    }
    
    public Order createOrder(OrderDto orderDto) {
        Order order = // 创建订单逻辑
        
        // 增加计数
        orderCounter.increment();
        
        return order;
    }
}

@Service
public class UserService {
    
    private final AtomicInteger activeUsers = new AtomicInteger(0);
    
    public UserService(MeterRegistry meterRegistry) {
        // 注册仪表,实时报告当前值
        meterRegistry.gauge("users.active", activeUsers);
    }
    
    public void userLogin() {
        activeUsers.incrementAndGet();
    }
    
    public void userLogout() {
        activeUsers.decrementAndGet();
    }
}

@Service
public class PaymentService {
    
    private final Timer paymentTimer;
    
    public PaymentService(MeterRegistry meterRegistry) {
        this.paymentTimer = Timer.builder("payments.processing")
            .description("Payment processing time")
            .tag("method", "credit_card")
            .register(meterRegistry);
    }
    
    public PaymentResult processPayment(PaymentRequest request) {
        return paymentTimer.record(() -> {
            // 计时执行支付逻辑
            return doProcessPayment(request);
        });
    }
}

@Service
public class FileService {
    
    private final DistributionSummary fileSizeSummary;
    
    public FileService(MeterRegistry meterRegistry) {
        this.fileSizeSummary = DistributionSummary.builder("files.uploaded.size")
            .description("Size of uploaded files")
            .baseUnit("bytes")
            .tags("type", "image")
            .register(meterRegistry);
    }
    
    public void uploadFile(MultipartFile file) {
        // 记录文件大小分布
        fileSizeSummary.record(file.getSize());
        
        // 上传逻辑
    }
}

@RestController
@RequestMapping("/api/metrics")
public class MetricsController {
    
    @Autowired
    private MeterRegistry meterRegistry;
    
    @GetMapping("/custom")
    public Map<String, Object> getCustomMetrics() {
        Map<String, Object> metrics = new HashMap<>();
        
        // 订单总数
        Counter orderCounter = meterRegistry.find("orders.created").counter();
        if (orderCounter != null) {
            metrics.put("totalOrders", orderCounter.count());
        }
        
        // 活跃用户数
        Gauge activeUsers = meterRegistry.find("users.active").gauge();
        if (activeUsers != null) {
            metrics.put("activeUsers", activeUsers.value());
        }
        
        // 支付平均耗时
        Timer paymentTimer = meterRegistry.find("payments.processing").timer();
        if (paymentTimer != null) {
            metrics.put("avgPaymentTime", paymentTimer.mean(java.util.concurrent.TimeUnit.MILLISECONDS));
        }
        
        return metrics;
    }
}

@RestController
@RequestMapping("/api/users")
@Timed(value = "user.api", description = "User API metrics")
public class UserController {
    
    @GetMapping
    @Timed(value = "user.api.list", description = "List users", percentiles = {0.5, 0.95, 0.99})
    public List<User> getAllUsers() {
        return userService.findAll();
    }
    
    @GetMapping("/{id}")
    @Timed(value = "user.api.get", description = "Get user by ID")
    public User getUser(@PathVariable Long id) {
        return userService.findById(id);
    }
}

global:
  scrape_interval: 15s
  evaluation_interval: 15s

scrape_configs:
  - job_name: 'spring-boot-app'
    metrics_path: '/actuator/prometheus'
    static_configs:
      - targets: ['localhost:8080']
    relabel_configs:
      - source_labels: [__address__]
        target_label: instance

{
  "title": "Spring Boot Application",
  "panels": [
    {
      "title": "JVM Memory",
      "type": "graph",
      "targets": [
        {
          "expr": "jvm_memory_used_bytes{area=\"heap\"}",
          "legendFormat": "Heap Used"
        },
        {
          "expr": "jvm_memory_max_bytes{area=\"heap\"}",
          "legendFormat": "Heap Max"
        }
      ]
    },
    {
      "title": "HTTP Requests",
      "type": "graph",
      "targets": [
        {
          "expr": "rate(http_server_requests_seconds_count[5m])",
          "legendFormat": "{{uri}}"
        }
      ]
    },
    {
      "title": "Response Time (P95)",
      "type": "graph",
      "targets": [
        {
          "expr": "histogram_quantile(0.95, rate(http_server_requests_seconds_bucket[5m]))",
          "legendFormat": "{{uri}}"
        }
      ]
    }
  ]
}

groups:
  - name: spring_boot_alerts
    rules:
      # 应用健康检查失败
      - alert: ApplicationDown
        expr: up{job="spring-boot-app"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Application {{ $labels.instance }} is down"
          description: "{{ $labels.instance }} has been down for more than 1 minute"
      
      # JVM堆内存使用率过高
      - alert: HighHeapMemoryUsage
        expr: (jvm_memory_used_bytes{area="heap"} / jvm_memory_max_bytes{area="heap"}) * 100 > 85
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High heap memory usage on {{ $labels.instance }}"
          description: "Heap memory usage is {{ $value }}%"
      
      # HTTP错误率过高
      - alert: HighErrorRate
        expr: rate(http_server_requests_seconds_count{status=~"5.."}[5m]) / rate(http_server_requests_seconds_count[5m]) * 100 > 5
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "High error rate on {{ $labels.instance }}"
          description: "Error rate is {{ $value }}%"
      
      # 响应时间过长
      - alert: SlowResponseTime
        expr: histogram_quantile(0.95, rate(http_server_requests_seconds_bucket[5m])) > 1
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Slow response time on {{ $labels.instance }}"
          description: "P95 response time is {{ $value }}s"

<dependency>
    <groupId>org.springframework.boot</groupId>
    <artifactId>spring-boot-starter-actuator</artifactId>
</dependency>

<!-- 分布式追踪 -->
<dependency>
    <groupId>io.micrometer</groupId>
    <artifactId>micrometer-tracing-bridge-brave</artifactId>
</dependency>
<dependency>
    <groupId>io.zipkin.reporter2</groupId>
    <artifactId>zipkin-reporter-brave</artifactId>
</dependency>

<!-- 或使用 OpenTelemetry -->
<dependency>
    <groupId>io.micrometer</groupId>
    <artifactId>micrometer-tracing-bridge-otel</artifactId>
</dependency>
<dependency>
    <groupId>io.opentelemetry</groupId>
    <artifactId>opentelemetry-exporter-zipkin</artifactId>
</dependency>

management:
  tracing:
    enabled: true
    sampling:
      probability: 1.0  # 采样率(生产环境建议0.1)
  zipkin:
    tracing:
      endpoint: http://localhost:9411/api/v2/spans

@Service
public class OrderService {
    
    @Autowired
    private Tracer tracer;
    
    public Order createOrder(OrderDto orderDto) {
        // 创建自定义Span
        Span span = tracer.nextSpan().name("create-order");
        
        try (Tracer.SpanInScope ws = tracer.withSpan(span.start())) {
            // 业务逻辑
            Order order = doCreateOrder(orderDto);
            
            // 添加事件
            span.event("order.created");
            
            // 添加标签
            span.tag("order.id", order.getId().toString());
            span.tag("order.amount", order.getAmount().toString());
            
            return order;
        } finally {
            span.end();
        }
    }
}

@Configuration
public class ObservabilityConfig {
    
    @Bean
    ObservedAspect observedAspect(ObservationRegistry registry) {
        return new ObservedAspect(registry);
    }
}

@Service
public class PaymentService {
    
    @Observed(name = "payment.process", 
              contextualName = "process-payment",
              lowCardinalityKeyValues = {"paymentType", "credit_card"})
    public PaymentResult processPayment(PaymentRequest request) {
        // 自动创建观察
        return doProcessPayment(request);
    }
}

management:
  endpoints:
    web:
      exposure:
        include: "*"
  endpoint:
    health:
      show-details: always
    env:
      show-values: always

management:
  endpoints:
    web:
      exposure:
        include: health,info,metrics,prometheus
      base-path: /actuator
  endpoint:
    health:
      show-details: when_authorized
      probes:
        enabled: true
    env:
      enabled: false
    heapdump:
      enabled: false
    threaddump:
      enabled: false
  # 注:management.security.enabled 在 Boot 2.0 起已移除,访问控制请使用 Spring Security(见下节)

@Configuration
public class ActuatorSecurityConfig {
    
    @Bean
    public SecurityFilterChain actuatorSecurityFilterChain(HttpSecurity http) throws Exception {
        http
            .requestMatcher(EndpointRequest.toAnyEndpoint())
            .authorizeHttpRequests(authz -> authz
                .requestMatchers(EndpointRequest.to("health", "info", "prometheus")).permitAll()
                .anyRequest().hasRole("ACTUATOR")
            )
            .httpBasic(withDefaults());
        
        return http.build();
    }
}

# 仅内网访问
server:
  port: 8080

management:
  server:
    port: 8081  # 使用独立端口
    address: 0.0.0.0  # 或限制为内网IP: 192.168.1.100

management:
  endpoints:
    web:
      exposure:
        include: health,info,prometheus
  metrics:
    tags:
      application: ${spring.application.name}
    distribution:
      percentiles-histogram:
        http.server.requests: true
      percentiles:
        http.server.requests: 0.5,0.95,0.99
    web:
      server:
        request:
          autotime:
            enabled: true
            percentiles: 0.5,0.95,0.99

src/main/java/com/example/ecommerce/
├── config/
│   ├── ActuatorConfig.java
│   ├── MetricsConfig.java
│   └── ObservabilityConfig.java
├── metrics/
│   ├── OrderMetrics.java
│   ├── UserMetrics.java
│   └── PaymentMetrics.java
├── health/
│   ├── DatabaseHealthIndicator.java
│   ├── RedisHealthIndicator.java
│   └── ExternalServiceHealthIndicator.java
└── controller/
    └── MetricsController.java

@Component
public class DatabaseHealthIndicator implements HealthIndicator {
    
    @Autowired
    private DataSource dataSource;
    
    @Override
    public Health health() {
        try (Connection connection = dataSource.getConnection()) {
            // 执行简单查询验证数据库连接
            try (Statement stmt = connection.createStatement();
                 ResultSet rs = stmt.executeQuery("SELECT 1")) {
                
                if (rs.next()) {
                    return Health.up()
                        .withDetail("database", "MySQL")
                        .withDetail("validationQuery", "SELECT 1")
                        .build();
                }
            }
        } catch (SQLException e) {
            return Health.down()
                .withDetail("error", e.getMessage())
                .build();
        }
        
        return Health.unknown().build();
    }
}

@Component
public class RedisHealthIndicator implements HealthIndicator {
    
    @Autowired
    private RedisTemplate<String, Object> redisTemplate;
    
    @Override
    public Health health() {
        try {
            // 执行PING命令
            String result = redisTemplate.getConnectionFactory()
                .getConnection()
                .ping();
            
            if ("PONG".equalsIgnoreCase(result)) {
                return Health.up()
                    .withDetail("redis", "available")
                    .build();
            } else {
                return Health.down()
                    .withDetail("redis", "unavailable")
                    .build();
            }
        } catch (Exception e) {
            return Health.down()
                .withDetail("error", e.getMessage())
                .build();
        }
    }
}

@Component
public class OrderMetrics {
    
    private final Counter orderCounter;
    private final Counter orderSuccessCounter;
    private final Counter orderFailureCounter;
    private final Timer orderProcessingTimer;
    private final DistributionSummary orderAmountSummary;
    
    public OrderMetrics(MeterRegistry meterRegistry) {
        // 订单总数
        this.orderCounter = Counter.builder("orders.total")
            .description("Total number of orders")
            .tag("type", "all")
            .register(meterRegistry);
        
        // 成功订单数
        this.orderSuccessCounter = Counter.builder("orders.total")
            .description("Total number of successful orders")
            .tag("status", "success")
            .register(meterRegistry);
        
        // 失败订单数
        this.orderFailureCounter = Counter.builder("orders.total")
            .description("Total number of failed orders")
            .tag("status", "failure")
            .register(meterRegistry);
        
        // 订单处理时间
        this.orderProcessingTimer = Timer.builder("orders.processing.time")
            .description("Order processing time")
            .register(meterRegistry);
        
        // 订单金额分布
        this.orderAmountSummary = DistributionSummary.builder("orders.amount")
            .description("Order amount distribution")
            .baseUnit("yuan")
            .register(meterRegistry);
    }
    
    public void recordOrderCreated() {
        orderCounter.increment();
    }
    
    public void recordOrderSuccess() {
        orderSuccessCounter.increment();
    }
    
    public void recordOrderFailure() {
        orderFailureCounter.increment();
    }
    
    public Timer.Sample startTimer() {
        return Timer.start();
    }
    
    public void recordProcessingTime(Timer.Sample sample) {
        sample.stop(orderProcessingTimer);
    }
    
    public void recordOrderAmount(double amount) {
        orderAmountSummary.record(amount);
    }
}

@Service
public class OrderService {
    
    @Autowired
    private OrderMetrics orderMetrics;
    
    @Autowired
    private Tracer tracer;
    
    public Order createOrder(OrderDto orderDto) {
        // 开始计时
        Timer.Sample sample = orderMetrics.startTimer();
        
        // 创建Span
        Span span = tracer.nextSpan().name("create-order");
        
        try (Tracer.SpanInScope ws = tracer.withSpan(span.start())) {
            // 创建订单
            Order order = doCreateOrder(orderDto);
            
            // 记录指标
            orderMetrics.recordOrderCreated();
            orderMetrics.recordOrderSuccess();
            orderMetrics.recordOrderAmount(order.getAmount());
            
            // 记录事件
            span.event("order.created");
            span.tag("order.id", order.getId().toString());
            
            return order;
        } catch (Exception e) {
            // 记录失败
            orderMetrics.recordOrderFailure();
            
            span.event("order.creation.failed");
            span.tag("error", e.getMessage());
            
            throw new IllegalStateException("创建订单失败", e);
        } finally {
            // 记录处理时间
            orderMetrics.recordProcessingTime(sample);
            
            span.end();
        }
    }
}

# × 错误:配置了Actuator但没有接入监控系统
management:
  endpoints:
    web:
      exposure:
        include: "*"

# √ 正确:接入Prometheus等监控系统
management:
  endpoints:
    web:
      exposure:
        include: health,info,prometheus
  prometheus:
    metrics:
      export:
        enabled: true

// × 错误:只检查应用是否存活
@Component
public class SimpleHealthIndicator implements HealthIndicator {
    @Override
    public Health health() {
        return Health.up().build();
    }
}

// √ 正确:检查所有关键依赖
@Component
public class CompositeHealthIndicator implements HealthIndicator {
    
    @Autowired
    private DataSource dataSource;
    
    @Autowired
    private RedisTemplate redisTemplate;
    
    @Override
    public Health health() {
        Health.Builder builder = Health.up();
        
        // 检查数据库
        try (Connection conn = dataSource.getConnection()) {
            builder.withDetail("database", "up");
        } catch (SQLException e) {
            builder.down().withDetail("database", "down");
        }
        
        // 检查Redis
        try {
            redisTemplate.getConnectionFactory().getConnection().ping();
            builder.withDetail("redis", "up");
        } catch (Exception e) {
            builder.down().withDetail("redis", "down");
        }
        
        return builder.build();
    }
}

# × 错误:暴露所有端点
management:
  endpoints:
    web:
      exposure:
        include: "*"

# √ 正确:只暴露必要端点,且限制访问
management:
  endpoints:
    web:
      exposure:
        include: health,info,prometheus
  server:
    port: 8081  # 独立端口,内网访问

// × 错误:只监控CPU、内存等机器指标

// √ 正确:同时监控业务指标
@Component
public class BusinessMetrics {
    
    private final Counter orderCounter;
    private final Timer orderTimer;
    
    public BusinessMetrics(MeterRegistry registry) {
        // 订单业务指标
        this.orderCounter = Counter.builder("business.orders")
            .description("Business order count")
            .register(registry);
        
        this.orderTimer = Timer.builder("business.order.processing")
            .description("Order processing time")
            .register(registry);
    }
}

# × 错误:只使用health端点
management:
  endpoints:
    web:
      exposure:
        include: health

# √ 正确:全面使用可观测性能力
management:
  endpoints:
    web:
      exposure:
        include: health,info,metrics,prometheus
  metrics:
    distribution:
      percentiles-histogram:
        http.server.requests: true
  tracing:
    enabled: true

@Component
public class CustomHealthIndicator implements HealthIndicator {
    
    @Override
    public Health health() {
        // 检查逻辑
        if (checkPassed()) {
            return Health.up()
                .withDetail("key", "value")
                .build();
        } else {
            return Health.down()
                .withDetail("error", "message")
                .build();
        }
    }
}

@Service
public class OrderService {
    
    private final Counter orderCounter;
    
    public OrderService(MeterRegistry registry) {
        this.orderCounter = Counter.builder("orders.total")
            .description("Total orders")
            .register(registry);
    }
    
    public void createOrder() {
        orderCounter.increment();
    }
}

@Observed(name = "payment.process")
public PaymentResult processPayment() {
    // 自动观察
}

# 查看当前日志级别
GET /actuator/loggers/com.example

# 修改日志级别
POST /actuator/loggers/com.example
Content-Type: application/json

{
  "configuredLevel": "DEBUG"
}

groups:
  - name: app_alerts
    rules:
      - alert: HighErrorRate
        expr: rate(http_server_requests_seconds_count{status=~"5.."}[5m]) / rate(http_server_requests_seconds_count[5m]) > 0.05
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "High error rate detected"

# 配置HikariCP指标
spring:
  datasource:
    hikari:
      register-mbeans: true

各服务 Actuator → Prometheus → Grafana → AlertManager
                                    ↓
                               统一Dashboard