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
161 lines
5.2 KiB
YAML
161 lines
5.2 KiB
YAML
---
|
|
# Gitea CI runner — general-purpose (legion)
|
|
# Docker socket REMOVED. Builds go through buildkitd TCP endpoint.
|
|
# Set DOCKER_HOST=tcp://buildkitd.ci.svc.cluster.local:1234 in build steps.
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: gitea-runner
|
|
namespace: ci
|
|
labels:
|
|
app: gitea-runner
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: gitea-runner
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: gitea-runner
|
|
annotations:
|
|
config-version: "2026-04-25-buildkit-no-sock"
|
|
spec:
|
|
securityContext:
|
|
runAsNonRoot: false # act_runner needs root for container management
|
|
initContainers:
|
|
- name: register
|
|
image: registry.neuralplatform.ai/ci-base:latest
|
|
workingDir: /data
|
|
command: ["/bin/sh", "-c"]
|
|
args:
|
|
- |
|
|
act_runner register \
|
|
--instance "$GITEA_INSTANCE_URL" \
|
|
--token "$GITEA_RUNNER_REGISTRATION_TOKEN" \
|
|
--name legion \
|
|
--labels "self-hosted:docker://registry.neuralplatform.ai/ci-base:latest,ubuntu-latest:docker://registry.neuralplatform.ai/ci-base:latest,ubuntu-24.04:docker://registry.neuralplatform.ai/ci-base:latest,linux,x64" \
|
|
--no-interactive
|
|
cat > /data/config.yaml << 'EOF'
|
|
runner:
|
|
capacity: 2
|
|
timeout: 3h
|
|
container:
|
|
network: host
|
|
docker_host: "tcp://buildkitd.ci.svc.cluster.local:1234"
|
|
force_pull: false
|
|
valid_volumes: []
|
|
default_image: "registry.neuralplatform.ai/ci-base:latest"
|
|
extra_hosts:
|
|
- "gitea.git.svc.cluster.local:10.43.1.53"
|
|
EOF
|
|
envFrom:
|
|
- secretRef:
|
|
name: gitea-runner-secret
|
|
volumeMounts:
|
|
- name: data
|
|
mountPath: /data
|
|
containers:
|
|
- name: runner
|
|
image: registry.neuralplatform.ai/ci-base:latest
|
|
workingDir: /data
|
|
command: ["act_runner", "daemon", "--config", "/data/config.yaml"]
|
|
env:
|
|
- name: DOCKER_HOST
|
|
value: "tcp://buildkitd.ci.svc.cluster.local:1234"
|
|
envFrom:
|
|
- secretRef:
|
|
name: gitea-runner-secret
|
|
volumeMounts:
|
|
- name: data
|
|
mountPath: /data
|
|
# docker-sock volume intentionally removed — use buildkitd TCP instead
|
|
resources:
|
|
requests:
|
|
memory: 512Mi
|
|
cpu: 250m
|
|
limits:
|
|
memory: 4Gi
|
|
cpu: "4"
|
|
volumes:
|
|
- name: data
|
|
emptyDir: {}
|
|
# docker-sock hostPath intentionally removed
|
|
---
|
|
# Neuron Technologies CI runner
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: neuron-technologies-runner
|
|
namespace: ci
|
|
labels:
|
|
app: neuron-technologies-runner
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: neuron-technologies-runner
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: neuron-technologies-runner
|
|
annotations:
|
|
config-version: "2026-04-25-buildkit-no-sock"
|
|
spec:
|
|
initContainers:
|
|
- name: register
|
|
image: registry.neuralplatform.ai/ci-base:latest
|
|
workingDir: /data
|
|
command: ["/bin/sh", "-c"]
|
|
args:
|
|
- |
|
|
act_runner register \
|
|
--instance "$GITEA_INSTANCE_URL" \
|
|
--token "$GITEA_RUNNER_REGISTRATION_TOKEN" \
|
|
--name neuron-technologies \
|
|
--labels "self-hosted:docker://registry.neuralplatform.ai/ci-base:latest,ubuntu-latest:docker://registry.neuralplatform.ai/ci-base:latest,ubuntu-24.04:docker://registry.neuralplatform.ai/ci-base:latest,linux,x64" \
|
|
--no-interactive
|
|
cat > /data/config.yaml << 'EOF'
|
|
runner:
|
|
capacity: 2
|
|
timeout: 3h
|
|
container:
|
|
network: host
|
|
docker_host: "tcp://buildkitd.ci.svc.cluster.local:1234"
|
|
force_pull: false
|
|
valid_volumes: []
|
|
default_image: "registry.neuralplatform.ai/ci-base:latest"
|
|
extra_hosts:
|
|
- "gitea.git.svc.cluster.local:10.43.1.53"
|
|
EOF
|
|
envFrom:
|
|
- secretRef:
|
|
name: neuron-technologies-runner-secret
|
|
volumeMounts:
|
|
- name: data
|
|
mountPath: /data
|
|
containers:
|
|
- name: runner
|
|
image: registry.neuralplatform.ai/ci-base:latest
|
|
workingDir: /data
|
|
command: ["act_runner", "daemon", "--config", "/data/config.yaml"]
|
|
env:
|
|
- name: DOCKER_HOST
|
|
value: "tcp://buildkitd.ci.svc.cluster.local:1234"
|
|
envFrom:
|
|
- secretRef:
|
|
name: neuron-technologies-runner-secret
|
|
volumeMounts:
|
|
- name: data
|
|
mountPath: /data
|
|
resources:
|
|
requests:
|
|
memory: 512Mi
|
|
cpu: 250m
|
|
limits:
|
|
memory: 4Gi
|
|
cpu: "4"
|
|
volumes:
|
|
- name: data
|
|
emptyDir: {}
|