feat: add OpenTelemetry SDK setup with feature flag

Set up the NodeSDK with OTLP/HTTP trace exporter, gated behind
ENABLE_OTEL=true. Uses 1% sampling by default to limit collector
load. Auto-instruments HTTP, Express and MongoDB while disabling
high-volume fs and Redis instrumentations.

Issue: CLDSRV-884

Author: delthas

index.js

@@ -7,4 +7,7 @@ require('werelogs').stderrUtils.catchAndTimestampStderr(
     require('cluster').isPrimary ? 1 : null,
 );
 
+// Initialize OpenTelemetry SDK before everything else
+require('./lib/otel.js');
+
 require('./lib/server.js')();

lib/otel.js

@@ -0,0 +1,58 @@
+'use strict';
+
+const enableOtel = process.env.ENABLE_OTEL === 'true';
+
+let sdk = null;
+
+if (enableOtel) {
+    const { NodeSDK } = require('@opentelemetry/sdk-node');
+    const { Resource } = require('@opentelemetry/resources');
+    const { OTLPTraceExporter } = require('@opentelemetry/exporter-trace-otlp-http');
+    const { getNodeAutoInstrumentations } = require('@opentelemetry/auto-instrumentations-node');
+    const { TraceIdRatioBasedSampler } = require('@opentelemetry/sdk-trace-base');
+    const { version } = require('../package.json');
+
+    const exportUrl = process.env.OTEL_EXPORTER_OTLP_TRACES_ENDPOINT ||
+        'http://otel-collector.default.svc.cluster.local:4318/v1/traces';
+
+    const traceExporter = new OTLPTraceExporter({
+        url: exportUrl,
+    });
+
+    const parsedRatio = parseFloat(process.env.OTEL_SAMPLING_RATIO);
+    const samplingRatio = Number.isFinite(parsedRatio) ? parsedRatio : 0.01;
+
+    sdk = new NodeSDK({
+        resource: new Resource({
+            'service.name': process.env.OTEL_SERVICE_NAME || 'cloudserver',
+            'service.version': process.env.OTEL_SERVICE_VERSION || version,
+            'service.namespace': process.env.OTEL_SERVICE_NAMESPACE || 'scality',
+        }),
+        traceExporter,
+        sampler: new TraceIdRatioBasedSampler(samplingRatio),
+        instrumentations: [
+            getNodeAutoInstrumentations({
+                '@opentelemetry/instrumentation-fs': { enabled: false },
+                '@opentelemetry/instrumentation-redis': { enabled: false },
+                '@opentelemetry/instrumentation-redis-4': { enabled: false },
+                '@opentelemetry/instrumentation-http': { enabled: true },
+                '@opentelemetry/instrumentation-express': { enabled: true },
+                '@opentelemetry/instrumentation-mongodb': {
+                    enabled: true,
+                    enhancedDatabaseReporting: true,
+                    useCollectionName: false,
+                    captureCommandDetails: false,
+                },
+                '@opentelemetry/instrumentation-aws-sdk': { enabled: false },
+            }),
+        ],
+    });
+
+    sdk.start();
+
+    const shutdown = () => sdk.shutdown().catch(() => {});
+    process.on('SIGTERM', shutdown);
+    process.on('SIGINT', shutdown);
+}
+
+module.exports = { sdk };

package.json

@@ -29,6 +29,12 @@
     "@aws-sdk/signature-v4": "^3.374.0",
     "@azure/storage-blob": "^12.28.0",
     "@hapi/joi": "^17.1.1",
+    "@opentelemetry/api": "^1.9.0",
+    "@opentelemetry/auto-instrumentations-node": "^0.50.2",
+    "@opentelemetry/exporter-trace-otlp-http": "^0.55.0",
+    "@opentelemetry/resources": "^1.30.1",
+    "@opentelemetry/sdk-node": "^0.55.0",
+    "@opentelemetry/sdk-trace-base": "^1.28.0",
     "@smithy/node-http-handler": "^3.0.0",
     "arsenal": "git+https://github.com/scality/Arsenal#8.3.8",
     "async": "2.6.4",