Files
Arkie-Library-Frontend/.gitea/workflows/deploy.yml
TerryM 8c1dd8189e
All checks were successful
Deploy to Frontend Servers / deploy (push) Successful in 1m0s
ci(deploy): make runner cleanup more aggressive to prevent ENOSPC
A previous deploy failed at the vite chunk-writing stage with
"ENOSPC: no space left on device". The cleanup step ran at the start
of the job but left enough stale data behind that the runner filled up
before `npm run build` could finish.

- Drop the act workspace retention from 60min to 10min. Closely-spaced
  pushes used to keep multiple stale jobs around; 10min still preserves
  any currently-running job because its mtime keeps advancing.
- Drop _work / setup-node / npm cacache retention from 24h to 60min.
- Drop the `until=24h` filter on docker prune so dangling images,
  containers, and builder cache get reclaimed every run.
- Add a second "Ensure free space before build" guard right before the
  Build step. If <3GB is free, aggressively prune act caches, npm
  cacache, and docker volumes before vite starts writing chunks.
2026-06-07 19:59:18 +08:00

152 lines
5.4 KiB
YAML

name: Deploy to Frontend Servers
on:
push:
branches:
- main
jobs:
deploy:
runs-on: self-hosted
steps:
- name: Free disk space
run: |
set +e
echo "=== Disk before cleanup ==="
df -h
# Stale act runner workspaces. Closely-spaced pushes (e.g. 3 commits
# within 30min) used to leak workspaces because the old 60min
# threshold left them in place. 10min is tight but still keeps any
# currently-running job's dir (its mtime updates as it writes).
if [ -d "$HOME/.cache/act" ]; then
du -sh "$HOME/.cache/act" 2>/dev/null
find "$HOME/.cache/act" -mindepth 1 -maxdepth 1 -type d -mmin +10 -exec rm -rf {} + 2>/dev/null
fi
# Stale runner workspaces and node setup/npm caches: 60min is plenty
# since each job re-fetches deps via `npm ci`.
for dir in "$HOME/actions-runner/_work" "$HOME/.cache/setup-node" "$HOME/.npm/_cacache"; do
if [ -d "$dir" ]; then
find "$dir" -mindepth 1 -maxdepth 2 -mmin +60 -exec rm -rf {} + 2>/dev/null
fi
done
# Docker leftovers: drop the `until=24h` filter so any dangling images
# / containers / builder cache get reclaimed every run.
if command -v docker >/dev/null 2>&1; then
docker image prune -af 2>/dev/null
docker container prune -f 2>/dev/null
docker builder prune -af 2>/dev/null
fi
# Stale /tmp files older than 2h, keep currently-running runner files.
find /tmp -mindepth 1 -maxdepth 1 -mmin +120 \
-not -name 'runner*' -not -name 'act*' \
-exec rm -rf {} + 2>/dev/null
echo "=== Disk after cleanup ==="
df -h
exit 0
- name: Checkout code
uses: actions/checkout@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: "22"
cache: npm
- name: Install dependencies
run: npm ci
- name: Type check
run: npx tsc --noEmit
- name: Format check
run: npm run format:check
- name: Test
run: npm test
- name: Ensure free space before build
run: |
# Second-pass guard right before the heaviest step. `npm ci` plus
# tsc/test pull in tons of files since the first cleanup ran, and
# vite chunk writes need at least a few GB free — ENOSPC here is what
# killed past runs.
set +e
AVAIL_MB=$(df -Pm . | awk 'NR==2 {print $4}')
echo "Available on workspace volume: ${AVAIL_MB} MB"
if [ "${AVAIL_MB:-0}" -lt 3072 ]; then
echo "<3GB free — running an aggressive cleanup before build."
rm -rf "$HOME/.cache/act"/*/hostexecutor/node_modules/.cache 2>/dev/null
rm -rf "$HOME/.npm/_cacache" 2>/dev/null
if command -v docker >/dev/null 2>&1; then
docker system prune -af --volumes 2>/dev/null
fi
df -h
fi
exit 0
- name: Build
run: npm run build
env:
VITE_API_URL: ""
VITE_API_PREFIX: "/apnew"
VITE_DISABLE_ADMIN: "true"
- name: Setup SSH key
run: |
mkdir -p ~/.ssh
echo "${{ secrets.DEPLOY_KEY }}" > ~/.ssh/deploy_key
chmod 600 ~/.ssh/deploy_key
ssh-keyscan -H ${{ secrets.FRONTEND_1_HOST }} >> ~/.ssh/known_hosts 2>/dev/null
ssh-keyscan -H ${{ secrets.FRONTEND_2_HOST }} >> ~/.ssh/known_hosts 2>/dev/null
- name: Deploy to both servers
run: |
set -euo pipefail
deploy_to() {
local HOST=$1
echo ">>> 部署到 $HOST"
rsync -avz --delete \
-e "ssh -i ~/.ssh/deploy_key -o StrictHostKeyChecking=no" \
dist/ \
ec2-user@${HOST}:/var/www/ark-library/
echo ">>> $HOST 部署完成"
}
deploy_to "${{ secrets.FRONTEND_1_HOST }}" &
PID1=$!
deploy_to "${{ secrets.FRONTEND_2_HOST }}" &
PID2=$!
FAIL=0
wait $PID1 || { echo "ERROR: frontend-1 部署失败"; FAIL=1; }
wait $PID2 || { echo "ERROR: frontend-2 部署失败"; FAIL=1; }
[ $FAIL -eq 0 ] || exit 1
echo "=== 两台都部署完成 ==="
- name: Verify both servers match local build
run: |
set -euo pipefail
LOCAL=$(sha256sum dist/index.html | awk '{print $1}')
SUM1=$(ssh -i ~/.ssh/deploy_key -o StrictHostKeyChecking=no \
ec2-user@${{ secrets.FRONTEND_1_HOST }} \
"sha256sum /var/www/ark-library/index.html | awk '{print \$1}'")
SUM2=$(ssh -i ~/.ssh/deploy_key -o StrictHostKeyChecking=no \
ec2-user@${{ secrets.FRONTEND_2_HOST }} \
"sha256sum /var/www/ark-library/index.html | awk '{print \$1}'")
echo "local: $LOCAL"
echo "frontend-1: $SUM1"
echo "frontend-2: $SUM2"
if [ "$SUM1" != "$LOCAL" ]; then
echo "ERROR: frontend-1 不是本次构建的版本"
exit 1
fi
if [ "$SUM2" != "$LOCAL" ]; then
echo "ERROR: frontend-2 不是本次构建的版本"
exit 1
fi
echo "✓ 两台都已经更新到本次构建的版本。"
- name: Cleanup SSH key
if: always()
run: rm -f ~/.ssh/deploy_key