fix(neuron-mcp): blue/green deployment, memory limits, preStop drain hook

- Rename Deployment to neuron-mcp-blue with slot=blue label - Add neuron-mcp-green Deployment scaffold (replicas=0, ready to receive new image) - Service selector now routes by slot label; annotation tracks active slot - Memory: 768Mi → 1536Mi limit, 256Mi → 512Mi request (fixes OOM pod restarts / 502s) - Add JAVA_TOOL_OPTIONS: container-aware GC + ExitOnOutOfMemoryError - Add preStop sleep 8s so Traefik drains in-flight connections before pod terminates - terminationGracePeriodSeconds: 30 - Add scripts/blue-green-deploy.sh: automated slot-swap with health check and rollback
2026-04-24 22:08:12 -05:00
parent 5d4cc17829
commit f86ee04467
4 changed files with 173 additions and 7 deletions
@@ -0,0 +1,76 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: neuron-mcp-green
+  namespace: neuron-prod
+  labels:
+    app: neuron-mcp
+    slot: green
+    env: prod
+spec:
+  # Scaled to 0 when inactive. Deploy process scales to 1, verifies health, then switches service.
+  replicas: 0
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: neuron-mcp
+      slot: green
+  template:
+    metadata:
+      labels:
+        app: neuron-mcp
+        slot: green
+        env: prod
+    spec:
+      terminationGracePeriodSeconds: 30
+      containers:
+        - name: neuron-mcp
+          # IMAGE UPDATED HERE before scaling to 1
+          image: registry.neuralplatform.ai/neuron-technologies/neuron-mcp:v0.8.3
+          imagePullPolicy: Always
+          ports:
+            - name: http
+              containerPort: 8080
+          env:
+            - name: OTEL_EXPORTER_OTLP_ENDPOINT
+              value: "http://alloy.monitoring.svc.cluster.local:4318"
+            - name: JAVA_TOOL_OPTIONS
+              value: "-XX:+UseContainerSupport -XX:MaxRAMPercentage=75.0 -XX:+ExitOnOutOfMemoryError"
+          envFrom:
+            - configMapRef:
+                name: neuron-prod-config
+            - secretRef:
+                name: neuron-prod-secrets
+          volumeMounts:
+            - name: data
+              mountPath: /data
+          resources:
+            requests:
+              cpu: 250m
+              memory: 512Mi
+            limits:
+              cpu: 1500m
+              memory: 1536Mi
+          lifecycle:
+            preStop:
+              exec:
+                command: ["sh", "-c", "sleep 8"]
+          livenessProbe:
+            httpGet:
+              path: /actuator/health/liveness
+              port: http
+            initialDelaySeconds: 30
+            periodSeconds: 30
+            failureThreshold: 3
+          readinessProbe:
+            httpGet:
+              path: /actuator/health/readiness
+              port: http
+            initialDelaySeconds: 10
+            periodSeconds: 10
+            failureThreshold: 3
+      volumes:
+        - name: data
+          persistentVolumeClaim:
+            claimName: neuron-prod-data