@Service
public class OrderMetrics {

    private final Counter orderCreatedCounter;
    private final Counter orderCancelledCounter;
    private final Timer orderCreationTimer;
    private final Gauge pendingOrdersGauge;

    public OrderMetrics(MeterRegistry registry, OrderRepository orderRepo) {
        this.orderCreatedCounter = Counter.builder("orderflow.orders.created")
            .description("إجمالي الطلبات المنشأة")
            .tag("service", "orderflow")
            .register(registry);

        this.orderCancelledCounter = Counter.builder("orderflow.orders.cancelled")
            .description("إجمالي الطلبات الملغاة")
            .register(registry);

        this.orderCreationTimer = Timer.builder("orderflow.orders.creation.duration")
            .description("مدة إنشاء الطلب")
            .publishPercentiles(0.5, 0.95, 0.99)
            .publishPercentileHistogram()
            .register(registry);

        this.pendingOrdersGauge = Gauge.builder("orderflow.orders.pending",
                orderRepo, repo -> repo.countByStatus("PENDING"))
            .description("عدد الطلبات المعلقة الحالي")
            .register(registry);
    }

    public void recordOrderCreated() {
        orderCreatedCounter.increment();
    }

    public Timer.Sample startCreationTimer() {
        return Timer.start(orderCreationTimer);
    }

    public void recordCreationComplete(Timer.Sample sample) {
        sample.stop(orderCreationTimer);
    }
}

// التنفيذ ناجح

@Service
public class OrderServiceImpl implements OrderService {

    private final OrderMetrics metrics;

    @Override
    @Transactional
    public Order createOrder(CreateOrderRequest request) {
        Timer.Sample sample = metrics.startCreationTimer();
        try {
            Order order = doCreateOrder(request);
            metrics.recordOrderCreated();
            return order;
        } finally {
            metrics.recordCreationComplete(sample);
        }
    }
}

// التنفيذ ناجح

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

// التنفيذ ناجح

# application.yml
management:
  endpoints:
    web:
      exposure:
        include: health,prometheus,metrics
  metrics:
    tags:
      application: ${spring.application.name}
    export:
      prometheus:
        enabled: true

# prometheus.yml
scrape_configs:
  - job_name: 'orderflow'
    metrics_path: '/actuator/prometheus'
    scrape_interval: 15s
    static_configs:
      - targets: ['orderflow:8080']

تم تحميل تهيئة المراقبة
أهداف Prometheus: 3 نشطة
لوحة Grafana: جاهزة

# استعلامات PromQL
# زمن استجابة P99 لواجهة برمجة طلبات الطلبات
histogram_quantile(0.99, sum(rate(http_server_requests_seconds_bucket{uri=~"/api/v1/orders.*"}[5m])) by (le, uri))

# معدل الخطأ (استجابات 5xx)
sum(rate(http_server_requests_seconds_total{status=~"5.."}[5m]))
/
sum(rate(http_server_requests_seconds_total[5m]))

# طلبات في الدقيقة
rate(orderflow_orders_created_total[1m]) * 60

تم تطبيق التهيئة بنجاح

# alert_rules.yml
groups:
- name: orderflow
  rules:
  - alert: HighErrorRate
    expr: |
      sum(rate(http_server_requests_seconds_total{status=~"5.."}[5m]))
      / sum(rate(http_server_requests_seconds_total[5m])) > 0.001
    for: 5m
    labels:
      severity: critical
    annotations:
      summary: "معدل خطأ OrderFlow يتجاوز 0.1%"

  - alert: HighP99Latency
    expr: |
      histogram_quantile(0.99, sum(rate(http_server_requests_seconds_bucket[5m])) by (le)) > 0.1
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "زمن استجابة P99 لـ OrderFlow يتجاوز 100 مللي ثانية"

{
  "dashboard": {
    "title": "OrderFlow Observability",
    "panels": [
      {
        "title": "معدل الطلبات (QPS)",
        "type": "timeseries",
        "targets": [{
          "expr": "sum(rate(http_server_requests_seconds_total{application=\"orderflow-service\"}[5m]))"
        }]
      },
      {
        "title": "زمن استجابة P99",
        "type": "timeseries",
        "targets": [{
          "expr": "histogram_quantile(0.99, sum(rate(http_server_requests_seconds_bucket{application=\"orderflow-service\"}[5m])) by (le))"
        }]
      },
      {
        "title": "معدل الخطأ",
        "type": "gauge",
        "targets": [{
          "expr": "sum(rate(http_server_requests_seconds_total{application=\"orderflow-service\",status=~\"5..\"}[5m])) / sum(rate(http_server_requests_seconds_total{application=\"orderflow-service\"}[5m]))"
        }],
        "fieldConfig": {
          "defaults": {
            "thresholds": {
              "steps": [
                {"value": 0, "color": "green"},
                {"value": 0.001, "color": "red"}
              ]
            }
          }
        }
      }
    ]
  }
}

{
  "dashboard": {
    "title": "OrderFlow Observability",
    "panels": [
      {
        "title": "معدل الطلبات (QPS)",
        "type": "timeseries",
        "targets": [
          {
            "expr": "sum(rate(http_server_requests_seconds_total{application=\"orderflow-service\"}[5m]))"
          }
        ]
      },
      {
        "title": "زمن استجابة P99",
        "type": "timeseries",
        "targets": [
          {
            "expr": "histogram_quantile(0.99, sum(rate(http_server_request

<dependency>
    <groupId>io.opentelemetry.instrumentation</groupId>
    <artifactId>opentelemetry-spring-boot-starter</artifactId>
</dependency>

// التنفيذ ناجح

# application.yml
otel:
  exporter:
    otlp:
      endpoint: http://otel-collector:4317
  resource:
    attributes:
      service.name: orderflow-service
  traces:
    exporter: otlp

@Service
public class OrderService {

    private final Tracer tracer;

    public OrderService(Tracer tracer) {
        this.tracer = tracer;
    }

    public Order createOrder(CreateOrderRequest request) {
        Span span = tracer.spanBuilder("create-order")
            .setAttribute("product.id", request.productId())
            .setAttribute("quantity", request.quantity())
            .startSpan();

        try (Scope scope = span.makeCurrent()) {
            Order order = doCreateOrder(request);
            span.setAttribute("order.id", order.getId());
            return order;
        } catch (Exception e) {
            span.recordException(e);
            span.setStatus(StatusCode.ERROR, e.getMessage());
            throw e;
        } finally {
            span.end();
        }
    }
}

// التنفيذ ناجح

# docker-compose.observability.yml
version: "3.9"
services:
  prometheus:
    image: prom/prometheus:latest
    ports: ["9090:9090"]
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - ./alert_rules.yml:/etc/prometheus/alert_rules.yml

  grafana:
    image: grafana/grafana:latest
    ports: ["3000:3000"]
    environment:
      GF_SECURITY_ADMIN_PASSWORD: admin
    volumes:
      - grafana-data:/var/lib/grafana

  otel-collector:
    image: otel/opentelemetry-collector:latest
    ports: ["4317:4317", "4318:4318"]
    volumes:
      - ./otel-collector-config.yml:/etc/otelcol/config.yaml

  jaeger:
    image: jaegertracing/all-in-one:latest
    ports: ["16686:16686"]

  app:
    build: .
    ports: ["8080:8080"]
    environment:
      OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4317
      OTEL_SERVICE_NAME: orderflow-service
      MANAGEMENT_ENDPOINTS_WEB_EXPOSURE_INCLUDE: health,prometheus,metrics