Will Anderson
93358505fc
Security: - Drop ALL capabilities, enforce non-root, RuntimeDefault seccomp on neuron-mcp, neuron-rest, neuron-marketing pods - Add startup probes (150s window for JVM) so liveness doesn't fire early - Replace docker-sock hostPath with BuildKit rootless TCP endpoint (moby/buildkit:v0.19.0-rootless) — removes node root access from CI - Document full ESO AppRole migration path in cluster-secret-store.yaml Autoscaling & availability: - HPAs on mcp (1–6), rest (1–4), marketing (2–8) at 65–70% CPU - PodDisruptionBudgets (minAvailable: 1) on all three services - NetworkPolicy: default-deny-all in neuron-prod, explicit allow rules for Traefik ingress, intra-namespace, and egress to DNS/platform/vault Observability: - ServiceMonitors for mcp, rest, marketing (cross-namespace enabled in kube-prometheus-stack with serviceMonitorSelectorNilUsesHelmValues:false) - PrometheusRules: high error rate, high latency, crash loops, replica shortage, Postgres down/connections, backup failure, backup staleness Chart version pinning: - kube-prometheus-stack, loki, tempo, redis, alloy, postgres — all pinned to major-version ranges to block silent breaking upgrades Backup hardening: - restic:latest → restic:0.17.3 (deterministic image) - Weekly backup-verify CronJob: restores latest snapshot and validates SQL dump structure (≥5 CREATE TABLE, pg_dump header check) ArgoCD: - neuron-prod AppProject: scopes deploys to neuron-prod + platform ns, blacklists ClusterRole/ClusterRoleBinding/Namespace creation, automated sync window 2–6am UTC, manual always allowed
95 lines
2.8 KiB
YAML
95 lines
2.8 KiB
YAML
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: neuron-mcp-blue
|
|
namespace: neuron-prod
|
|
labels:
|
|
app: neuron-mcp
|
|
slot: blue
|
|
env: prod
|
|
spec:
|
|
replicas: 1
|
|
strategy:
|
|
type: Recreate
|
|
selector:
|
|
matchLabels:
|
|
app: neuron-mcp
|
|
slot: blue
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: neuron-mcp
|
|
slot: blue
|
|
env: prod
|
|
annotations:
|
|
kubectl.kubernetes.io/restartedAt: "2026-04-25T08:40:00Z"
|
|
spec:
|
|
terminationGracePeriodSeconds: 30
|
|
securityContext:
|
|
runAsNonRoot: true
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
containers:
|
|
- name: neuron-mcp
|
|
image: registry.neuralplatform.ai/neuron-technologies/neuron-mcp:v0.15.3
|
|
imagePullPolicy: Always
|
|
ports:
|
|
- name: http
|
|
containerPort: 8080
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
readOnlyRootFilesystem: false # JVM writes temp files; restrict paths via allowedPaths once profiled
|
|
runAsNonRoot: true
|
|
capabilities:
|
|
drop: ["ALL"]
|
|
env:
|
|
- name: OTEL_EXPORTER_OTLP_ENDPOINT
|
|
value: "http://alloy-otlp.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:
|
|
# Give Traefik time to drain in-flight connections before pod terminates
|
|
command: ["sh", "-c", "sleep 8"]
|
|
# startupProbe gives the JVM up to 150s to start before liveness takes over.
|
|
# Prevents false crash loops during slow cold starts.
|
|
startupProbe:
|
|
httpGet:
|
|
path: /actuator/health/liveness
|
|
port: http
|
|
failureThreshold: 30
|
|
periodSeconds: 5
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /actuator/health/liveness
|
|
port: http
|
|
periodSeconds: 30
|
|
failureThreshold: 3
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /actuator/health/readiness
|
|
port: http
|
|
initialDelaySeconds: 5
|
|
periodSeconds: 10
|
|
failureThreshold: 3
|
|
volumes:
|
|
- name: data
|
|
persistentVolumeClaim:
|
|
claimName: neuron-prod-data
|