josh/electric-cherry
1
0
Fork 0
Code Issues 18 Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add Watchdog recovery and drift rebuild workflows

Browse Source
This commit is contained in:
josh
2026-09-27 15:13:38 -04:00
parent a7044f21a1
commit b9f5902945
36 changed files with 2131 additions and 424 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/lib/server/provisioning/restarts.ts
+23 -11
View File
@@ -1,13 +1,14 @@
import { config } from '../config.js';
import { db } from '../db/index.js';
import { komodoInspectHealthy, komodoRestart, komodoRuntimeAction } from '../integrations/komodo.js';
import { rconStatusResult } from '../integrations/rcon.js';
import { probeServerStatus } from '../fleet/status-evidence.js';
import { deploymentStage, finishDeployment } from './history.js';
// Komodo queues restart work. Don't mistake the still-running old container
// for a completed restart when an API kick immediately follows the request.
const HEALTH_POLL_MS = 15_000;
const requestsInFlight = new Set<string>();
export const restartRequestInFlight = (server: string) => requestsInFlight.has(server);
interface RestartSlot {
server: string;
@@ -41,11 +42,14 @@ export function rolloutWaitReason(server: string, operationId = ''): string | nu
return 'Waiting for the current provisioning operation';
}
const slot = slotFor(server);
if (slot?.healthy_at === null) {
const ownHandoff = slot?.operation_id === operationId && !!db().prepare(`SELECT 1 FROM server_deployments d
WHERE d.id = ? AND d.action IN ('restart','rebuild') AND EXISTS (
SELECT 1 FROM provisioning_sources s WHERE s.operation_id = d.id AND s.kind = 'watchdog')`).get(operationId);
if (slot?.healthy_at === null && !ownHandoff) {
return `Waiting for the previous restart of this server to recover${slot.error ? `: ${slot.error}` : ''}`;
}
const { n } = db().prepare('SELECT COUNT(*) AS n FROM restart_rollout WHERE healthy_at IS NULL').get() as { n: number };
return n >= config.restartConcurrency ? 'Queued for a rolling restart; waiting for another server to recover' : null;
return n - (ownHandoff && slot?.healthy_at === null ? 1 : 0) >= config.restartConcurrency ? 'Queued for a rolling restart; waiting for another server to recover' : null;
}
export type RolloutRestartResult =
@@ -76,7 +80,7 @@ export async function restartInRollout(server: string, options: { operationId: s
const result = options.action === 'start' ? await komodoRuntimeAction(server, 'start') : await komodoRestart(server);
if (result.ok) {
db().prepare("UPDATE server_deployments SET state = 'awaiting-health' WHERE id = ?").run(operationId);
deploymentStage(operationId!, 'Waiting for container and RCON health');
deploymentStage(operationId!, 'Waiting for container and game health (RCON or fresh telemetry)');
return { kind: 'started' };
}
// These failures cannot have queued a remote restart. Other failures
@@ -115,6 +119,13 @@ async function refresh(): Promise<void> {
.all() as RestartSlot[];
for (const slot of slots) {
if (requestsInFlight.has(slot.server)) continue;
// Recovery capacity transferred to a rebuild remains reserved until
// teardown. Its health is verified by the creation worker, never here.
if (slot.operation_id && db().prepare(`SELECT 1 FROM server_deployments d WHERE d.id = ? AND (
(d.action = 'rebuild' AND d.state IN ('waiting','queued','running','awaiting-health'))
OR (d.action = 'restart' AND d.state = 'waiting' AND d.submitted_at IS NULL AND EXISTS (
SELECT 1 FROM provisioning_sources s WHERE s.operation_id = d.id AND s.kind = 'watchdog')))`)
.get(slot.operation_id)) continue;
if (Date.now() - Date.parse(slot.checked_at ?? slot.requested_at) < HEALTH_POLL_MS) continue;
let error: string | null = null;
let players: number | null = null;
@@ -123,22 +134,23 @@ async function refresh(): Promise<void> {
if (!health.ok) {
error = `unhealthy: ${health.reason}${health.snippet ? ` snippet=${health.snippet.slice(0, 400)}` : ''}`;
} else {
const rcon = await rconStatusResult(slot.server);
if (!rcon.ok) error = `rcon not answering: ${rcon.reason}`;
else players = rcon.status.players;
const status = await probeServerStatus(slot.server, slot.requested_at);
if (!status.ok) error = `rcon not answering and no fresh telemetry: ${status.reason}`;
else players = status.players;
}
} catch (err) {
error = `health check: ${(err as Error).message}`;
}
const now = new Date().toISOString();
db().prepare(`UPDATE restart_rollout SET checked_at = ?, healthy_at = ?, players = ?, error = ?
WHERE server = ? AND requested_at = ? AND healthy_at IS NULL`)
.run(now, error ? null : now, players, error, slot.server, slot.requested_at);
const checked = db().prepare(`UPDATE restart_rollout SET checked_at = ?, healthy_at = ?, players = ?, error = ?
WHERE server = ? AND requested_at = ? AND operation_id IS ? AND healthy_at IS NULL`)
.run(now, error ? null : now, players, error, slot.server, slot.requested_at, slot.operation_id);
if (!checked.changes) continue;
if (slot.operation_id && db().prepare("SELECT 1 FROM server_deployments WHERE id = ? AND state = 'awaiting-health'").get(slot.operation_id)) {
db().prepare('UPDATE server_deployments SET checked_at = ?, players = ? WHERE id = ?').run(now, players, slot.operation_id);
if (error) deploymentStage(slot.operation_id, 'Waiting for health: ' + error);
else {
deploymentStage(slot.operation_id, 'Verified container and RCON health');
deploymentStage(slot.operation_id, 'Verified container and game health (RCON or fresh telemetry)');
finishDeployment(slot.operation_id, { ok: true });
}
}