claude
8f2f6d1684
Build and Deploy Verso / deploy (push) Failing after 1s
The TeX Live layer (~3.5 GB) failed to push to registry.alocoq.fr:
Traefik severed the upload mid-stream ("client disconnected during blob
PUT ... unexpected EOF"), buildkit retried at the wrong offset, and the
registry returned "blob upload invalid".
Push to the in-cluster registry Service (registry.git.svc.cluster.local:5000)
instead, so the upload never traverses Traefik. Changes:
- buildctl outputs use registry.insecure=true (registry is plain HTTP)
- add a verso-buildkitd-config ConfigMap with buildkitd.toml marking the
registry http/insecure, so the second build can pull the base image back
- the verso Deployment and rolling update reference the in-cluster image
NOTE: the cluster nodes' containerd must also treat
registry.git.svc.cluster.local:5000 as an insecure registry, otherwise
the kubelet image pull for the test deployment will fail. That is node-
level config outside this repo.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
293 lines
9.3 KiB
YAML
293 lines
9.3 KiB
YAML
name: Build and Deploy Verso
|
|
|
|
on:
|
|
push:
|
|
branches:
|
|
- main
|
|
workflow_dispatch:
|
|
|
|
env:
|
|
SITE_URL: https://test.alocoq.fr
|
|
|
|
jobs:
|
|
deploy:
|
|
runs-on: native
|
|
timeout-minutes: 240
|
|
|
|
steps:
|
|
- name: Build and push Verso images with BuildKit
|
|
run: |
|
|
kubectl -n ci delete job verso-buildkit --ignore-not-found=true --wait=true
|
|
|
|
# buildkitd config: mark the in-cluster registry as http (insecure)
|
|
# so the second build can resolve/pull the base image we just pushed.
|
|
cat <<'EOF' | kubectl apply -f -
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: verso-buildkitd-config
|
|
namespace: ci
|
|
data:
|
|
buildkitd.toml: |
|
|
[registry."registry.git.svc.cluster.local:5000"]
|
|
http = true
|
|
insecure = true
|
|
EOF
|
|
|
|
cat <<'EOF' | kubectl apply -f -
|
|
apiVersion: batch/v1
|
|
kind: Job
|
|
metadata:
|
|
name: verso-buildkit
|
|
namespace: ci
|
|
spec:
|
|
backoffLimit: 0
|
|
template:
|
|
spec:
|
|
restartPolicy: Never
|
|
initContainers:
|
|
- name: prepare
|
|
image: alpine/git:latest
|
|
command: ["sh", "-c"]
|
|
args:
|
|
- |
|
|
set -eux
|
|
git clone --depth 1 https://git.alocoq.fr/alois/verso.git /workspace/repo
|
|
volumeMounts:
|
|
- name: workspace
|
|
mountPath: /workspace
|
|
|
|
containers:
|
|
- name: buildkit
|
|
image: moby/buildkit:latest
|
|
securityContext:
|
|
privileged: true
|
|
command: ["sh", "-c"]
|
|
args:
|
|
- |
|
|
set -eux
|
|
|
|
# Push to the in-cluster registry (plain HTTP) to bypass
|
|
# the Traefik ingress, whose read timeout was killing the
|
|
# multi-GB TeX Live layer upload mid-stream. The base
|
|
# image is pulled back in for the second build, so the
|
|
# registry must be marked insecure for both push and pull
|
|
# (buildkitd.toml handles the pull/resolve side).
|
|
REG=registry.git.svc.cluster.local:5000
|
|
|
|
buildctl-daemonless.sh build \
|
|
--frontend=dockerfile.v0 \
|
|
--local context=/workspace/repo \
|
|
--local dockerfile=/workspace/repo/server-ce \
|
|
--opt filename=Dockerfile-base \
|
|
--output type=image,name=$REG/verso-base:latest,push=true,registry.insecure=true
|
|
|
|
buildctl-daemonless.sh build \
|
|
--frontend=dockerfile.v0 \
|
|
--local context=/workspace/repo \
|
|
--local dockerfile=/workspace/repo/server-ce \
|
|
--opt filename=Dockerfile \
|
|
--opt build-arg:OVERLEAF_BASE_TAG=$REG/verso-base:latest \
|
|
--output type=image,name=$REG/verso:latest,push=true,registry.insecure=true
|
|
volumeMounts:
|
|
- name: workspace
|
|
mountPath: /workspace
|
|
- name: buildkitd-config
|
|
mountPath: /etc/buildkit
|
|
|
|
volumes:
|
|
- name: workspace
|
|
emptyDir: {}
|
|
- name: buildkitd-config
|
|
configMap:
|
|
name: verso-buildkitd-config
|
|
EOF
|
|
|
|
- name: Wait for build
|
|
run: |
|
|
kubectl -n ci wait --for=condition=complete job/verso-buildkit --timeout=14400s
|
|
|
|
- name: Show build logs
|
|
if: always()
|
|
run: |
|
|
kubectl -n ci logs job/verso-buildkit -c prepare || true
|
|
kubectl -n ci logs job/verso-buildkit -c buildkit || true
|
|
|
|
- name: Recreate test dependencies
|
|
run: |
|
|
kubectl -n test delete deployment mongo redis --ignore-not-found=true --wait=true
|
|
kubectl -n test delete service mongo redis --ignore-not-found=true --wait=true
|
|
|
|
cat <<'EOF' | kubectl apply -f -
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: mongo
|
|
namespace: test
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: mongo
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: mongo
|
|
spec:
|
|
containers:
|
|
- name: mongo
|
|
image: mongo:8
|
|
command: ["mongod", "--replSet", "rs0", "--bind_ip_all"]
|
|
ports:
|
|
- containerPort: 27017
|
|
volumeMounts:
|
|
- name: mongo-data
|
|
mountPath: /data/db
|
|
volumes:
|
|
- name: mongo-data
|
|
emptyDir: {}
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: mongo
|
|
namespace: test
|
|
spec:
|
|
selector:
|
|
app: mongo
|
|
ports:
|
|
- name: mongo
|
|
port: 27017
|
|
targetPort: 27017
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: redis
|
|
namespace: test
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: redis
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: redis
|
|
spec:
|
|
containers:
|
|
- name: redis
|
|
image: redis:7
|
|
ports:
|
|
- containerPort: 6379
|
|
volumeMounts:
|
|
- name: redis-data
|
|
mountPath: /data
|
|
volumes:
|
|
- name: redis-data
|
|
emptyDir: {}
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: redis
|
|
namespace: test
|
|
spec:
|
|
selector:
|
|
app: redis
|
|
ports:
|
|
- name: redis
|
|
port: 6379
|
|
targetPort: 6379
|
|
EOF
|
|
|
|
kubectl -n test rollout status deployment/mongo --timeout=180s
|
|
kubectl -n test rollout status deployment/redis --timeout=180s
|
|
|
|
sleep 5
|
|
|
|
kubectl -n test exec deploy/mongo -- mongosh --eval '
|
|
rs.initiate({
|
|
_id: "rs0",
|
|
members: [{ _id: 0, host: "mongo:27017" }]
|
|
})
|
|
'
|
|
|
|
kubectl -n test exec deploy/mongo -- mongosh --eval '
|
|
while (rs.status().myState !== 1) {
|
|
sleep(1000)
|
|
}
|
|
print("Mongo replica set is PRIMARY")
|
|
'
|
|
|
|
- name: Ensure Verso deployment exists
|
|
run: |
|
|
cat <<'EOF' | kubectl apply -f -
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: verso
|
|
namespace: test
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: verso
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: verso
|
|
spec:
|
|
containers:
|
|
- name: verso
|
|
image: registry.git.svc.cluster.local:5000/verso:latest
|
|
ports:
|
|
- containerPort: 80
|
|
env:
|
|
- name: OVERLEAF_MONGO_URL
|
|
value: mongodb://mongo:27017/sharelatex?replicaSet=rs0
|
|
- name: OVERLEAF_REDIS_HOST
|
|
value: redis
|
|
- name: REDIS_HOST
|
|
value: redis
|
|
- name: OVERLEAF_APP_NAME
|
|
value: Verso
|
|
- name: OVERLEAF_SITE_URL
|
|
value: https://test.alocoq.fr
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: verso
|
|
namespace: test
|
|
spec:
|
|
selector:
|
|
app: verso
|
|
ports:
|
|
- name: http
|
|
port: 80
|
|
targetPort: 80
|
|
EOF
|
|
|
|
- name: Deploy Verso image
|
|
run: |
|
|
kubectl -n test set image deployment/verso \
|
|
verso=registry.git.svc.cluster.local:5000/verso:latest
|
|
|
|
kubectl -n test rollout restart deployment/verso
|
|
kubectl -n test rollout status deployment/verso --timeout=300s
|
|
|
|
- name: Create admin user
|
|
run: |
|
|
sleep 20
|
|
kubectl -n test exec deploy/verso -- bash -lc '
|
|
cd /overleaf/services/web
|
|
node modules/server-ce-scripts/scripts/create-user \
|
|
--admin \
|
|
--email=test@example.com || true
|
|
'
|
|
|
|
- name: Cleanup
|
|
if: always()
|
|
run: |
|
|
kubectl -n ci delete job verso-buildkit --ignore-not-found=true --wait=true |