Skip to content

Introduce a cron job that syncs the prod base into staging #633

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Oct 9, 2025
Merged

Introduce a cron job that syncs the prod base into staging #633

Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
c7672d5
Sync prod base to staging
rdimitrov Oct 8, 2025
ec6aa73
Use the existing backups of prod instead
rdimitrov Oct 8, 2025
d51f3ea
Add additional checks to ensure we are in staging
rdimitrov Oct 8, 2025
d4119e9
Update wrong comment
rdimitrov Oct 8, 2025
b94b056
Log out from prod once we got the backup credentials
rdimitrov Oct 8, 2025
f39faa6
Cleanup workflow a bit
domdomegg Oct 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
374 changes: 374 additions & 0 deletions .github/workflows/sync-db.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,374 @@
name: Sync Production DB to Staging (from backups)

on:
schedule:
# Run daily at 2 AM UTC (during low-traffic hours)
- cron: '0 2 * * *'
workflow_dispatch: # Allow manual triggering

permissions:
contents: read

jobs:
sync-database:
name: Sync Prod DB to Staging from k8up Backups
runs-on: ubuntu-latest
environment: staging
concurrency:
group: sync-staging-database
cancel-in-progress: false
steps:
- name: Authenticate to Google Cloud (Production)
uses: google-github-actions/auth@7c6bc770dae815cd3e89ee6cdf493a5fab2cc093
with:
credentials_json: ${{ secrets.GCP_PROD_SERVICE_ACCOUNT_KEY }}

- name: Setup Google Cloud SDK
uses: google-github-actions/setup-gcloud@aa5489c8933f4cc7a4f7d45035b3b1440c9c10db
with:
project_id: mcp-registry-prod
install_components: gke-gcloud-auth-plugin

- name: Get backup credentials from prod cluster
id: backup-creds
run: |
# Connect to prod cluster to get backup credentials
gcloud container clusters get-credentials mcp-registry-prod \
--zone=us-central1-b \
--project=mcp-registry-prod

# Extract backup credentials from prod cluster
ACCESS_KEY=$(kubectl get secret k8up-backup-credentials -n default -o jsonpath='{.data.AWS_ACCESS_KEY_ID}' | base64 -d)
SECRET_KEY=$(kubectl get secret k8up-backup-credentials -n default -o jsonpath='{.data.AWS_SECRET_ACCESS_KEY}' | base64 -d)

# Store in outputs (GitHub Actions encrypts these automatically)
echo "access_key=$ACCESS_KEY" >> $GITHUB_OUTPUT
echo "secret_key=$SECRET_KEY" >> $GITHUB_OUTPUT

echo "✓ Backup credentials extracted from prod"

- name: Switch to staging cluster
uses: google-github-actions/auth@7c6bc770dae815cd3e89ee6cdf493a5fab2cc093
with:
credentials_json: ${{ secrets.GCP_STAGING_SERVICE_ACCOUNT_KEY }}

- name: Configure staging cluster access
run: |
gcloud config set project mcp-registry-staging
gcloud container clusters get-credentials mcp-registry-staging \
--zone=us-central1-b \
--project=mcp-registry-staging

echo "✓ Connected to staging cluster"

- name: Create secret for prod backup bucket access
run: |
# Create/update secret in staging with read-only access to prod backups
kubectl create secret generic prod-backup-credentials \
--from-literal=AWS_ACCESS_KEY_ID="${{ steps.backup-creds.outputs.access_key }}" \
--from-literal=AWS_SECRET_ACCESS_KEY="${{ steps.backup-creds.outputs.secret_key }}" \
--dry-run=client -o yaml | kubectl apply -f -

echo "✓ Backup credentials configured in staging"

- name: Create restore PVC
run: |
kubectl apply -f - <<EOF
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: restore-data-pvc
namespace: default
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 50Gi
EOF

echo "✓ Restore PVC created"

- name: Trigger k8up restore from prod backups
id: restore
run: |
RESTORE_NAME="restore-from-prod-$(date +%Y%m%d-%H%M%S)"
echo "restore_name=$RESTORE_NAME" >> $GITHUB_OUTPUT

# Create a k8up Restore resource to restore from prod backups
kubectl apply -f - <<EOF
apiVersion: k8up.io/v1
kind: Restore
metadata:
name: $RESTORE_NAME
namespace: default
spec:
snapshot: latest
restoreMethod:
folder:
claimName: restore-data-pvc
backend:
repoPasswordSecretRef:
name: k8up-repo-password
key: password
s3:
bucket: mcp-registry-prod-backups
endpoint: https://storage.googleapis.com
accessKeyIDSecretRef:
name: prod-backup-credentials
key: AWS_ACCESS_KEY_ID
secretAccessKeySecretRef:
name: prod-backup-credentials
key: AWS_SECRET_ACCESS_KEY
EOF

echo "✓ k8up restore triggered: $RESTORE_NAME"

- name: Wait for k8up restore to complete
run: |
RESTORE_NAME="${{ steps.restore.outputs.restore_name }}"

echo "Waiting for restore job to start..."
sleep 15

# Find the job created by k8up for this restore
for i in {1..30}; do
JOB_NAME=$(kubectl get jobs -n default -l k8up.io/owned-by=restore -o jsonpath='{.items[?(@.metadata.ownerReferences[0].name=="'$RESTORE_NAME'")].metadata.name}' 2>/dev/null)
if [ -n "$JOB_NAME" ]; then
echo "Found restore job: $JOB_NAME"
break
fi
echo "Waiting for job to be created... ($i/30)"
sleep 2
done

if [ -z "$JOB_NAME" ]; then
echo "ERROR: Restore job not found"
kubectl get restore $RESTORE_NAME -n default -o yaml
exit 1
fi

# Wait for the restore job to complete (max 15 minutes)
kubectl wait --for=condition=complete \
job/$JOB_NAME \
--timeout=900s -n default || {
echo "Restore job failed or timed out"
kubectl describe job/$JOB_NAME -n default
kubectl logs job/$JOB_NAME -n default --tail=100
exit 1
}

echo "✓ k8up restore completed successfully"

- name: Find staging PostgreSQL PVC
id: pgdata-pvc
run: |
# Find the PVC used by the PostgreSQL cluster
PVC_NAME=$(kubectl get pvc -n default -l cnpg.io/cluster=registry-pg -o jsonpath='{.items[0].metadata.name}')

if [ -z "$PVC_NAME" ]; then
echo "ERROR: Could not find PostgreSQL PVC"
kubectl get pvc -n default -l cnpg.io/cluster=registry-pg
exit 1
fi

echo "pvc_name=$PVC_NAME" >> $GITHUB_OUTPUT
echo "✓ Found PostgreSQL PVC: $PVC_NAME"

- name: Scale down staging PostgreSQL
run: |
echo "Scaling down PostgreSQL cluster..."
kubectl patch cluster registry-pg -n default \
--type merge \
--patch '{"spec":{"instances":0}}'

# Wait for pods to terminate
echo "Waiting for pods to terminate..."
kubectl wait --for=delete pod -l cnpg.io/cluster=registry-pg -n default --timeout=300s || true

echo "✓ PostgreSQL scaled down"

- name: Replace staging database with restored backup
id: copy-job
run: |
JOB_NAME="copy-pgdata-$(date +%Y%m%d-%H%M%S)"
echo "job_name=$JOB_NAME" >> $GITHUB_OUTPUT

# Create a job to copy the restored backup data to the staging PVC
kubectl apply -f - <<EOF
apiVersion: batch/v1
kind: Job
metadata:
name: $JOB_NAME
namespace: default
spec:
ttlSecondsAfterFinished: 600
template:
spec:
restartPolicy: Never
containers:
- name: copy-data
image: busybox:latest
command:
- /bin/sh
- -c
- |
set -e
echo "Finding PostgreSQL data in backup..."
echo "Restore structure:"
find /restore -maxdepth 3 -type d 2>/dev/null | head -20

# Try different possible paths for pgdata
PGDATA_SOURCE=""
for path in \$(find /restore -type d -name "pgdata" 2>/dev/null); do
if [ -f "\$path/PG_VERSION" ]; then
PGDATA_SOURCE="\$path"
break
fi
done

if [ -z "\$PGDATA_SOURCE" ]; then
echo "ERROR: Could not find valid pgdata directory with PG_VERSION"
echo "Searched paths:"
find /restore -type d -name "pgdata" 2>/dev/null
exit 1
fi

echo "Found pgdata at: \$PGDATA_SOURCE"
echo "Contents:"
ls -lah \$PGDATA_SOURCE/ | head -10

echo "Backing up existing staging data..."
mkdir -p /pgdata-backup
if [ "\$(ls -A /pgdata)" ]; then
cp -a /pgdata/. /pgdata-backup/ || echo "Warning: Could not backup existing data"
fi

echo "Clearing existing data..."
rm -rf /pgdata/*

echo "Copying backup data to staging PVC..."
cp -a \$PGDATA_SOURCE/. /pgdata/

echo "Setting correct permissions..."
chmod 700 /pgdata

echo "✓ Data copy completed"
ls -lah /pgdata/ | head -20
echo "PostgreSQL version: \$(cat /pgdata/PG_VERSION)"
volumeMounts:
- name: restore-data
mountPath: /restore
- name: staging-pgdata
mountPath: /pgdata
volumes:
- name: restore-data
persistentVolumeClaim:
claimName: restore-data-pvc
- name: staging-pgdata
persistentVolumeClaim:
claimName: ${{ steps.pgdata-pvc.outputs.pvc_name }}
EOF

echo "✓ Copy job created: $JOB_NAME"

- name: Wait for data copy to complete
run: |
JOB_NAME="${{ steps.copy-job.outputs.job_name }}"

# Wait for copy to complete
kubectl wait --for=condition=complete job/$JOB_NAME --timeout=600s -n default || {
echo "Data copy job failed"
kubectl describe job/$JOB_NAME -n default
kubectl logs job/$JOB_NAME -n default --tail=100
exit 1
}

echo "✓ Database data replaced successfully"

- name: Scale up staging PostgreSQL
run: |
echo "Scaling up PostgreSQL cluster..."
kubectl patch cluster registry-pg -n default \
--type merge \
--patch '{"spec":{"instances":1}}'

# Wait for PostgreSQL pod to be created
echo "Waiting for PostgreSQL pod to be created..."
for i in {1..60}; do
POD_COUNT=$(kubectl get pods -l cnpg.io/cluster=registry-pg -n default --no-headers 2>/dev/null | wc -l)
if [ "$POD_COUNT" -gt 0 ]; then
echo "Pod created"
break
fi
echo "Waiting... ($i/60)"
sleep 2
done

# Wait for PostgreSQL to be ready
echo "Waiting for PostgreSQL to be ready..."
kubectl wait --for=condition=ready pod -l cnpg.io/cluster=registry-pg -n default --timeout=300s

echo "✓ PostgreSQL is running"

- name: Verify staging DB is functional
run: |
# Create a verification pod
kubectl run pg-verify-$(date +%s) \
--image=postgres:15 \
--rm -i --restart=Never \
--env="PGPASSWORD=$(kubectl get secret registry-pg-superuser -n default -o jsonpath='{.data.password}' | base64 -d)" \
-- bash -c '
echo "Waiting for database to accept connections..."
for i in {1..30}; do
if pg_isready -h registry-pg-rw -U postgres 2>/dev/null; then
break
fi
echo "Waiting... ($i/30)"
sleep 2
done

echo "Querying database..."
TABLE_COUNT=$(psql -h registry-pg-rw -U postgres -d app -tAc "SELECT COUNT(*) FROM information_schema.tables WHERE table_schema = '\''public'\'';" 2>&1)

if [ $? -ne 0 ]; then
echo "ERROR: Could not query database"
echo "$TABLE_COUNT"
exit 1
fi

if [ "$TABLE_COUNT" -lt 1 ]; then
echo "ERROR: Staging DB has no tables!"
exit 1
fi

echo "✓ Staging DB is healthy with $TABLE_COUNT tables"

echo "Top 10 tables by row count:"
psql -h registry-pg-rw -U postgres -d app \
-c "SELECT schemaname, tablename, n_live_tup FROM pg_stat_user_tables ORDER BY n_live_tup DESC LIMIT 10;" || true
'

echo "✓ Database verification completed"

- name: Cleanup
if: always()
run: |
# Clean up jobs first
if [ -n "${{ steps.copy-job.outputs.job_name }}" ]; then
kubectl delete job ${{ steps.copy-job.outputs.job_name }} -n default || true
fi

# Remove restore PVC (will wait for jobs to finish)
kubectl delete pvc restore-data-pvc -n default || true

# Remove prod backup credentials (for security)
kubectl delete secret prod-backup-credentials -n default || true

# Clean up old restore resources (keep last 3)
kubectl get restore -n default --sort-by=.metadata.creationTimestamp -o name | head -n -3 | xargs -r kubectl delete || true

# Clean up old copy jobs (keep last 3)
kubectl get jobs -n default --sort-by=.metadata.creationTimestamp -o name | grep 'copy-pgdata-' | head -n -3 | xargs -r kubectl delete -n default || true

echo "✓ Cleanup completed"
Loading