Aligns hyperguild's cd.yml with the cobalt-dingo reference pattern: - Add environment: staging to the deploy job - Add Flux reconcile trigger after infra repo push - Add polling wait for supervisor and ingestion image tags to propagate - Add rollout status verification for both deployments with failure diagnostics (pod status, events, describe)
194 lines
7.4 KiB
YAML
194 lines
7.4 KiB
YAML
name: cd
|
|
|
|
on:
|
|
workflow_run:
|
|
workflows: ["CI"]
|
|
types: [completed]
|
|
branches: [main]
|
|
|
|
jobs:
|
|
deploy:
|
|
name: Build and deploy
|
|
runs-on: self-hosted
|
|
if: ${{ github.event.workflow_run.conclusion == 'success' && github.event.workflow_run.event == 'push' }}
|
|
environment: staging
|
|
env:
|
|
SERVICE: supervisor
|
|
IMAGE: gitea.d-ma.be/mathias/supervisor
|
|
INGESTION_IMAGE: gitea.d-ma.be/mathias/ingestion
|
|
ROUTING_IMAGE: gitea.d-ma.be/mathias/routing
|
|
INFRA_REPO: git@gitea.d-ma.be:mathias/infra.git
|
|
BUILDKIT_HOST: unix:///run/buildkit/buildkitd.sock
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Build and push supervisor image
|
|
run: |
|
|
set -e
|
|
trap 'rm -f /tmp/supervisor-image.tar' EXIT
|
|
IMAGE_TAG="${{ github.sha }}"
|
|
echo "Building ${IMAGE}:${IMAGE_TAG}"
|
|
|
|
buildctl --addr "${BUILDKIT_HOST}" build \
|
|
--frontend dockerfile.v0 \
|
|
--local context=. \
|
|
--local dockerfile=. \
|
|
--opt build-arg:VERSION="${IMAGE_TAG}" \
|
|
--output type=oci,dest=/tmp/supervisor-image.tar
|
|
|
|
skopeo copy \
|
|
oci-archive:/tmp/supervisor-image.tar \
|
|
docker://${IMAGE}:${IMAGE_TAG} \
|
|
--dest-creds "${{ secrets.REGISTRY_CREDS }}"
|
|
|
|
echo "Built and pushed ${IMAGE}:${IMAGE_TAG}"
|
|
|
|
- name: Build and push ingestion image
|
|
run: |
|
|
set -e
|
|
trap 'rm -f /tmp/ingestion-image.tar' EXIT
|
|
IMAGE_TAG="${{ github.sha }}"
|
|
echo "Building ${INGESTION_IMAGE}:${IMAGE_TAG}"
|
|
|
|
buildctl --addr "${BUILDKIT_HOST}" build \
|
|
--frontend dockerfile.v0 \
|
|
--local context=ingestion \
|
|
--local dockerfile=ingestion \
|
|
--output type=oci,dest=/tmp/ingestion-image.tar
|
|
|
|
skopeo copy \
|
|
oci-archive:/tmp/ingestion-image.tar \
|
|
docker://${INGESTION_IMAGE}:${IMAGE_TAG} \
|
|
--dest-creds "${{ secrets.REGISTRY_CREDS }}"
|
|
|
|
echo "Built and pushed ${INGESTION_IMAGE}:${IMAGE_TAG}"
|
|
|
|
- name: Build and push routing image
|
|
run: |
|
|
set -e
|
|
trap 'rm -f /tmp/routing-image.tar' EXIT
|
|
IMAGE_TAG="${{ github.sha }}"
|
|
echo "Building ${ROUTING_IMAGE}:${IMAGE_TAG}"
|
|
|
|
buildctl --addr "${BUILDKIT_HOST}" build \
|
|
--frontend dockerfile.v0 \
|
|
--local context=. \
|
|
--local dockerfile=. \
|
|
--opt filename=Dockerfile.routing \
|
|
--opt build-arg:VERSION="${IMAGE_TAG}" \
|
|
--output type=oci,dest=/tmp/routing-image.tar
|
|
|
|
skopeo copy \
|
|
oci-archive:/tmp/routing-image.tar \
|
|
docker://${ROUTING_IMAGE}:${IMAGE_TAG} \
|
|
--dest-creds "${{ secrets.REGISTRY_CREDS }}"
|
|
|
|
echo "Built and pushed ${ROUTING_IMAGE}:${IMAGE_TAG}"
|
|
|
|
- name: Update infra repo
|
|
run: |
|
|
set -e
|
|
trap 'rm -rf /tmp/infra-update; rm -f ~/.ssh/infra_deploy_key' EXIT
|
|
IMAGE_TAG="${{ github.sha }}"
|
|
mkdir -p ~/.ssh
|
|
echo "${{ secrets.INFRA_DEPLOY_KEY }}" > ~/.ssh/infra_deploy_key
|
|
chmod 600 ~/.ssh/infra_deploy_key
|
|
printf 'Host gitea.d-ma.be\n HostName 127.0.0.1\n Port 30022\n StrictHostKeyChecking no\n' >> ~/.ssh/config
|
|
|
|
GIT_SSH_COMMAND="ssh -i ~/.ssh/infra_deploy_key -o IdentitiesOnly=yes" \
|
|
git clone "${INFRA_REPO}" /tmp/infra-update
|
|
|
|
cd /tmp/infra-update
|
|
|
|
sed -i "s|gitea.d-ma.be/mathias/supervisor:.*|gitea.d-ma.be/mathias/supervisor:${IMAGE_TAG}|" \
|
|
"k3s/apps/${SERVICE}/deployment.yaml"
|
|
|
|
sed -i "s|gitea.d-ma.be/mathias/ingestion:.*|gitea.d-ma.be/mathias/ingestion:${IMAGE_TAG}|" \
|
|
"k3s/apps/${SERVICE}/ingestion-deployment.yaml"
|
|
|
|
sed -i "s|gitea.d-ma.be/mathias/routing:.*|gitea.d-ma.be/mathias/routing:${IMAGE_TAG}|" \
|
|
"k3s/apps/routing/deployment.yaml"
|
|
|
|
git config user.email "cd-bot@d-ma.be"
|
|
git config user.name "CD Bot"
|
|
git add "k3s/apps/${SERVICE}/deployment.yaml" \
|
|
"k3s/apps/${SERVICE}/ingestion-deployment.yaml" \
|
|
"k3s/apps/routing/deployment.yaml"
|
|
git commit -m "chore(deploy): supervisor+ingestion+routing → ${IMAGE_TAG}"
|
|
GIT_SSH_COMMAND="ssh -i ~/.ssh/infra_deploy_key -o IdentitiesOnly=yes" \
|
|
git push
|
|
|
|
echo "Infra repo updated: ${SERVICE}+ingestion → ${IMAGE_TAG}"
|
|
|
|
- name: Trigger Flux reconcile (immediate)
|
|
run: |
|
|
kubectl -n flux-system annotate gitrepository flux-system \
|
|
reconcile.fluxcd.io/requestedAt="$(date +%s)" --overwrite
|
|
kubectl -n flux-system annotate kustomization apps \
|
|
reconcile.fluxcd.io/requestedAt="$(date +%s)" --overwrite
|
|
|
|
- name: Wait for Flux to apply new supervisor image
|
|
run: |
|
|
EXPECTED="gitea.d-ma.be/mathias/supervisor:${{ github.sha }}"
|
|
for i in $(seq 1 60); do
|
|
CURRENT=$(kubectl get deploy supervisor -n supervisor \
|
|
-o jsonpath='{.spec.template.spec.containers[0].image}' 2>/dev/null || echo "")
|
|
if [ "$CURRENT" = "$EXPECTED" ]; then
|
|
echo "✓ Flux applied supervisor image after ${i}s"
|
|
break
|
|
fi
|
|
sleep 1
|
|
done
|
|
kubectl get deploy supervisor -n supervisor \
|
|
-o jsonpath='{.spec.template.spec.containers[0].image}' \
|
|
| grep -qx "$EXPECTED" \
|
|
|| { echo "✗ Flux did not apply supervisor image within 60s"; exit 1; }
|
|
|
|
- name: Wait for Flux to apply new ingestion image
|
|
run: |
|
|
EXPECTED="gitea.d-ma.be/mathias/ingestion:${{ github.sha }}"
|
|
for i in $(seq 1 60); do
|
|
CURRENT=$(kubectl get deploy ingestion -n supervisor \
|
|
-o jsonpath='{.spec.template.spec.containers[0].image}' 2>/dev/null || echo "")
|
|
if [ "$CURRENT" = "$EXPECTED" ]; then
|
|
echo "✓ Flux applied ingestion image after ${i}s"
|
|
break
|
|
fi
|
|
sleep 1
|
|
done
|
|
kubectl get deploy ingestion -n supervisor \
|
|
-o jsonpath='{.spec.template.spec.containers[0].image}' \
|
|
| grep -qx "$EXPECTED" \
|
|
|| { echo "✗ Flux did not apply ingestion image within 60s"; exit 1; }
|
|
|
|
- name: Verify supervisor rollout
|
|
run: |
|
|
kubectl rollout status deployment/supervisor \
|
|
--namespace supervisor \
|
|
--timeout=120s \
|
|
|| {
|
|
echo "── pod status ──"
|
|
kubectl get pods -n supervisor -o wide
|
|
echo "── events ──"
|
|
kubectl get events -n supervisor --sort-by='.lastTimestamp' | tail -20
|
|
echo "── describe ──"
|
|
kubectl describe pods -n supervisor -l app=supervisor | tail -40
|
|
exit 1
|
|
}
|
|
|
|
- name: Verify ingestion rollout
|
|
run: |
|
|
kubectl rollout status deployment/ingestion \
|
|
--namespace supervisor \
|
|
--timeout=120s \
|
|
|| {
|
|
echo "── pod status ──"
|
|
kubectl get pods -n supervisor -o wide
|
|
echo "── events ──"
|
|
kubectl get events -n supervisor --sort-by='.lastTimestamp' | tail -20
|
|
echo "── describe ──"
|
|
kubectl describe pods -n supervisor -l app=ingestion | tail -40
|
|
exit 1
|
|
}
|