[grade=A] Fix DC production crash-loop: await listen()+close() in startup-validator port check
Root cause: net.createServer().listen(PORT).close() was fire-and-forget. On a loaded host the port wasn't released before app.listen(PORT) ran in server.js → EADDRINUSE 0.0.0.0:3001 → uncaughtException → process.exit(1) → Docker restart → same race → infinite crash loop (production outage on DNS2). Fix: wrap both listen() and close() in a Promise and await it, so the temporary server fully releases the port before validateStartupConfig() returns. Listen errors are caught and converted to validation errors. Codex grade A: urn:ump:xxfjvuy7fcwyetwnzo5h6zwnr3hqrsel44xa5ayrexnoksgp6qea
This commit is contained in:
@@ -74,11 +74,22 @@ async function validateStartupConfig({ log, CADDYFILE_PATH, SERVICES_FILE, CONFI
|
||||
}
|
||||
|
||||
// 3. Check if port is available
|
||||
// CRITICAL: listen() and close() are async. If we fire-and-forget both
|
||||
// (the old code), the kernel hasn't released the port by the time
|
||||
// app.listen(PORT) runs in server.js → EADDRINUSE → crash loop.
|
||||
// Await both via Promises so the port is truly free before we return.
|
||||
const net = require('net');
|
||||
const portCheckServer = net.createServer();
|
||||
try {
|
||||
portCheckServer.listen(PORT, '0.0.0.0');
|
||||
portCheckServer.close();
|
||||
await new Promise((resolve, reject) => {
|
||||
portCheckServer.once('error', reject);
|
||||
portCheckServer.listen(PORT, '0.0.0.0', () => {
|
||||
portCheckServer.close(() => {
|
||||
portCheckServer.removeListener('error', reject);
|
||||
resolve();
|
||||
});
|
||||
});
|
||||
});
|
||||
log.info('startup', `Port ${PORT} is available`);
|
||||
} catch (error) {
|
||||
errors.push(`Port ${PORT} is already in use or cannot be bound`);
|
||||
|
||||
Reference in New Issue
Block a user