Best Practice: Observability-Stack aufbauen

// Node.js Beispiel mit Winston und OpenTelemetry
const winston = require('winston');
const { trace, context } = require('@opentelemetry/api');

const logger = winston.createLogger({
  format: winston.format.combine(
    winston.format.timestamp(),
    winston.format.json()
  ),
  transports: [new winston.transports.Console()]
});

// Middleware: Trace-ID und Request-ID in jeden Log einbetten
function createLogContext() {
  const span = trace.getActiveSpan();
  const spanContext = span?.spanContext();

  return {
    trace_id: spanContext?.traceId || 'no-trace',
    span_id:  spanContext?.spanId  || 'no-span',
  };
}

// Verwendung:
logger.info('Payment processed', {
  ...createLogContext(),
  service:    'payment-service',
  request_id: req.headers['x-request-id'],
  user_id:    req.user.id,
  amount:     payment.amount,
  currency:   payment.currency,
});

// Erwartetes Log-Ausgabe-Format:
// {
//   "timestamp": "2025-03-18T10:30:00.000Z",
//   "level": "info",
//   "service": "payment-service",
//   "trace_id": "4bf92f3577b34da6a3ce929d0e0e4736",
//   "span_id": "00f067aa0ba902b7",
//   "request_id": "req-abc123",
//   "message": "Payment processed",
//   "amount": 99.99,
//   "currency": "EUR"
// }

// otel-setup.js – vor allem anderen importieren
const { NodeSDK } = require('@opentelemetry/sdk-node');
const { AWSXRayPropagator } = require('@opentelemetry/propagator-aws-xray');
const { AWSXRayIdGenerator } = require('@opentelemetry/id-generator-aws-xray');
const { AWSXRayLambdaPropagator } = require('@opentelemetry/propagator-aws-xray');
const { OTLPTraceExporter } = require('@opentelemetry/exporter-trace-otlp-http');
const { HttpInstrumentation } = require('@opentelemetry/instrumentation-http');
const { ExpressInstrumentation } = require('@opentelemetry/instrumentation-express');

const sdk = new NodeSDK({
  textMapPropagator: new AWSXRayPropagator(),
  idGenerator: new AWSXRayIdGenerator(),
  traceExporter: new OTLPTraceExporter({
    url: process.env.OTEL_EXPORTER_OTLP_ENDPOINT || 'http://localhost:4318/v1/traces',
  }),
  instrumentations: [
    new HttpInstrumentation(),
    new ExpressInstrumentation(),
  ],
  serviceName: process.env.SERVICE_NAME || 'payment-service',
});

sdk.start();
process.on('SIGTERM', () => sdk.shutdown());

# CloudWatch Log Group für Applikation
resource "aws_cloudwatch_log_group" "app" {
  name              = "/aws/ecs/${var.service_name}"
  retention_in_days = 90  # 90 Tage für Applikations-Logs

  tags = {
    service     = var.service_name
    environment = var.environment
    managed-by  = "terraform"
  }
}

# CloudWatch Log Group für Security/Audit-Logs (längere Retention)
resource "aws_cloudwatch_log_group" "audit" {
  name              = "/audit/${var.service_name}"
  retention_in_days = 365  # 1 Jahr für Audit-Logs

  tags = {
    service     = var.service_name
    environment = var.environment
    log-type    = "audit"
  }
}

# CloudWatch Contributor Insights (Anomalie-Erkennung in Logs)
resource "aws_cloudwatch_log_metric_filter" "error_rate" {
  name           = "${var.service_name}-error-rate"
  pattern        = "{ $.level = \"ERROR\" }"
  log_group_name = aws_cloudwatch_log_group.app.name

  metric_transformation {
    name      = "ErrorCount"
    namespace = "PaymentService"
    value     = "1"
  }
}

# X-Ray Sampling-Regel konfigurieren
resource "aws_xray_sampling_rule" "payment_service" {
  rule_name      = "payment-service-sampling"
  priority       = 1000
  reservoir_size = 5     # Minimum 5 Traces/Sekunde
  fixed_rate     = 0.05  # 5% Sampling für normale Requests
  url_path       = "/api/payment/*"
  host           = "*"
  http_method    = "*"
  service_type   = "*"
  service_name   = "payment-service"
  resource_arn   = "*"
  version        = 1
}

resource "aws_cloudwatch_dashboard" "service_health" {
  dashboard_name = "${var.service_name}-health"

  dashboard_body = jsonencode({
    widgets = [
      {
        type   = "metric"
        width  = 8
        height = 6
        properties = {
          title  = "Request Rate (RPM)"
          period = 60
          stat   = "Sum"
          metrics = [["PaymentService", "RequestCount"]]
        }
      },
      {
        type   = "metric"
        width  = 8
        height = 6
        properties = {
          title  = "Error Rate (%)"
          period = 60
          stat   = "Average"
          metrics = [["PaymentService", "ErrorRate"]]
        }
      },
      {
        type   = "metric"
        width  = 8
        height = 6
        properties = {
          title  = "p99 Latency (ms)"
          period = 60
          stat   = "p99"
          metrics = [["PaymentService", "Latency"]]
        }
      }
    ]
  })
}