Observabilitas

# prometheus/rules/alerts.yml
groups:
  - name: yomu-alerts
    rules:
      - alert: ServiceDown
        expr: up == 0
        for: 1m
        annotations:
          summary: "Service {{ $labels.job }} down"
          description: "{{ $labels.job }} tidak merespon selama 1 menit"
      
      - alert: HighErrorRate
        expr: rate(traefik_service_requests_total{code=~"5.."}[5m]) > 0.1
        for: 5m
        annotations:
          summary: "High error rate detected"
          description: "Error rate > 10% pada {{ $labels.service }}"
      
      - alert: JavaHeapHigh
        expr: jvm_memory_used_bytes / jvm_memory_max_bytes > 0.85
        for: 5m
        annotations:
          summary: "JVM heap usage high"
          description: "Heap usage > 85% pada {{ $labels.job }}"
      
      - alert: ContainerHighCPU
        expr: rate(container_cpu_usage_seconds_total[5m]) > 0.8
        for: 5m
        annotations:
          summary: "Container CPU usage high"
          description: "CPU usage > 80% pada {{ $labels.name }}"
      
      - alert: ContainerHighMemory
        expr: container_memory_usage_bytes / container_spec_memory_limit_bytes > 0.9
        for: 5m
        annotations:
          summary: "Container memory usage high"
          description: "Memory usage > 90% pada {{ $labels.name }}"
      
      - alert: HighLatency
        expr: histogram_quantile(0.95, rate(traefik_service_request_duration_seconds_bucket[5m])) > 2
        for: 5m
        annotations:
          summary: "High latency detected"
          description: "P95 latency > 2s pada {{ $labels.service }}"

{service="java"} |= "ERROR"
{service="rust-staging"} |= "panic" | json
{service="frontend"} |= "API call failed"

-javaagent:/app/otel/opentelemetry-javaagent.jar
-Dotel.resource.attributes=service.name=java-backend
-Dotel.exporter.otlp.endpoint=http://otel-collector:4317

OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4317
OTEL_SERVICE_NAME=rust-backend