cd.yml's own $HOME (/data) is a PVC that persists across job runs on
this runner. The previous fix (cb9c251) appended the corrected
HostName to ~/.ssh/config, but a stale 127.0.0.1:30022 entry from an
earlier failed run was already there — ssh_config is first-match-wins,
so the stale entry silently shadowed the fix and the very next run
failed identically. Cleaned the persisted stale entry on the runner
directly; this commit removes the append entirely so the step no
longer depends on file state surviving (or not surviving) between
runs — CLI -o overrides always win. Verified end-to-end against the
real infra repo from inside the runner pod (git ls-remote, correctly
reached gitea and got a clean auth rejection, not a connection error).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Roq1ajWKR5f1hG5Df9wC6A
122 lines
5.1 KiB
YAML
122 lines
5.1 KiB
YAML
name: cd
|
|
|
|
"on":
|
|
workflow_run:
|
|
workflows: ["CI"]
|
|
types: [completed]
|
|
branches: [main]
|
|
|
|
jobs:
|
|
deploy:
|
|
name: Build and deploy
|
|
runs-on: self-hosted
|
|
if: ${{ github.event.workflow_run.conclusion == 'success' && github.event.workflow_run.event == 'push' }}
|
|
environment: staging
|
|
env:
|
|
INGESTION_IMAGE: git.d-ma.be/mathias/ingestion
|
|
INFRA_REPO: git@git.d-ma.be:mathias/infra.git
|
|
BUILDKIT_HOST: unix:///run/buildkit/buildkitd.sock
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Build and push ingestion image
|
|
run: |
|
|
set -e
|
|
trap 'rm -f /tmp/ingestion-image.tar' EXIT
|
|
IMAGE_TAG="${{ 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: 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
|
|
# In-cluster DNS to gitea's SSH NodePort service, not 127.0.0.1:30022
|
|
# (that only worked when act_runner ran on koala's bare host network;
|
|
# from inside the containerized runner's own pod netns, loopback
|
|
# never reaches the host — "Connection refused", found 2026-07-27).
|
|
#
|
|
# Pass as -o overrides on the ssh invocation itself, NOT appended to
|
|
# ~/.ssh/config: $HOME (/data) is a PVC that persists across job
|
|
# runs on this runner (same "workspace not ephemeral" class as
|
|
# brain: act-runner-host-executor-tmp-persists), so an appended
|
|
# line here would pile up duplicate `Host git.d-ma.be` blocks
|
|
# across every run — ssh_config is first-match-wins, so a stale
|
|
# entry from an earlier failed run would silently shadow this
|
|
# fix forever (exactly what happened once already: this fix's
|
|
# own first attempt got appended AFTER an already-stale entry
|
|
# and lost). CLI -o options always win regardless of file state,
|
|
# so this step is safe to re-run any number of times.
|
|
GIT_SSH_COMMAND="ssh -i ~/.ssh/infra_deploy_key -o IdentitiesOnly=yes -o HostName=gitea-ssh-nodeport.gitea.svc.cluster.local -o Port=22 -o StrictHostKeyChecking=no" \
|
|
git clone "${INFRA_REPO}" /tmp/infra-update
|
|
|
|
cd /tmp/infra-update
|
|
|
|
sed -i "s|git.d-ma.be/mathias/ingestion:.*|git.d-ma.be/mathias/ingestion:${IMAGE_TAG}|" \
|
|
"k3s/apps/supervisor/ingestion-deployment.yaml"
|
|
|
|
git config user.email "cd-bot@d-ma.be"
|
|
git config user.name "CD Bot"
|
|
git add "k3s/apps/supervisor/ingestion-deployment.yaml"
|
|
git commit -m "chore(deploy): ingestion → ${IMAGE_TAG}"
|
|
GIT_SSH_COMMAND="ssh -i ~/.ssh/infra_deploy_key -o IdentitiesOnly=yes" \
|
|
git push
|
|
|
|
echo "Infra repo updated: 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="$(date +%s)" --overwrite
|
|
|
|
- name: Wait for Flux to apply new ingestion image
|
|
run: |
|
|
EXPECTED="git.d-ma.be/mathias/ingestion:${{ 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 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
|
|
}
|