mirror of
https://github.com/wekan/wekan.git
synced 2026-11-05 21:44:59 -05:00
Lauri Ojansivu
5a1c9a61e9
Motivated by the 10.16-10.21 reports where, after an upgrade, the login page showed "Must be logged in" or sat on the logo + "Loading, please wait." spinner, pages took 5+ minutes, All Boards counts stayed 0 and i18n showed raw keys — the FerretDB v1 (SQLite) process pegged ~2 cores for a long time under WeKan's poll load, i.e. a migration/repair or a saturated backend, with no way to see it without the Admin Panel. Server-side, independent of any client / progress page: - server/startup/repairBoardsOnStartup.js runs the shared board data-repairs once (version-gated, background, 30s after boot) so corrupted data is fixed even if no user opens a board and nobody watches a progress page. - The MongoDB <-> SQLite text migration and the startup repair now PERSIST their progress to the text_migration_status collection (models/textMigrationStatus.js), so a separate process can see "a migration/repair is in progress" (an in-memory object could not). Status overview (server/lib/systemStatus.js), shown in Admin Panel / Problems -> Summary and via the method systemStatusReport (admin-gated, server/methods/ systemStatus.js): - everything in progress (text migration, board repair, recovery, cron migration, attachment migration) aggregated from the persisted status collections; - detected problems (broken cards; failing login-page checks); - login-page "Must be logged in" / "Loading, please wait" cause checklist (migration in progress, ROOT_URL, LDAP, Sandstorm) — models/lib/loginProblems.js; - a CPU detail area that calls out a pegged ferretdb process and the mitigation. Snap: `snap run wekan.problems` (snap-src/bin/wekan-problems[.mjs], snapcraft app `problems`) prints the same overview as text — problems, migrations/repairs in progress, login checks — so an admin with only server access can see it WITHOUT Admin Panel access. Sub-commands: migrations | login | broken-cards | cpu | help. Pure helpers models/lib/loginProblems.js and models/lib/problemsOverview.js are unit-tested; tests/problemsStatus.test.cjs (14 checks) also source-guards the server hub, method, startup pass, migration persistence and snap command. Thanks to xet7 !
65 lines
2.5 KiB
JavaScript
65 lines
2.5 KiB
JavaScript
import { Meteor } from 'meteor/meteor';
|
|
import os from 'os';
|
|
import { ReactiveCache } from '/imports/reactiveCache';
|
|
import {
|
|
getProblemsOverview,
|
|
getInProgress,
|
|
getLoginProblems,
|
|
} from '/server/lib/systemStatus';
|
|
|
|
// Admin-gated methods behind the Admin Panel / Problems "Status" overview. The
|
|
// same data is available without the Admin Panel via `snap run wekan.problems`.
|
|
|
|
async function requireAdmin() {
|
|
const user = await ReactiveCache.getCurrentUser();
|
|
if (!user || !user.isAdmin) {
|
|
throw new Meteor.Error('not-authorized', 'Admin only');
|
|
}
|
|
return user;
|
|
}
|
|
|
|
// Problem-specific detail, mirroring the `snap run wekan.problems <area>`
|
|
// sub-commands. Kept in one place so the Admin Panel and the snap command agree.
|
|
function cpuDetail() {
|
|
const cpus = os.cpus() || [];
|
|
const mem = process.memoryUsage();
|
|
return {
|
|
area: 'cpu',
|
|
title: 'CPU usage',
|
|
loadAverage: os.loadavg(), // 1 / 5 / 15 min
|
|
cpuCount: cpus.length,
|
|
cpuModel: cpus.length ? cpus[0].model : '',
|
|
uptimeSeconds: Math.round(process.uptime()),
|
|
rssBytes: mem.rss,
|
|
heapUsedBytes: mem.heapUsed,
|
|
note: 'Load average is machine-wide (1/5/15 min). rss/heap are the WeKan server process. Sustained load near or above the CPU count means the machine is saturated. If `top` shows the ferretdb process pegged near 100%/200% for a long time, the FerretDB v1 (SQLite) backend is saturated under WeKan\'s poll load (symptoms: pages take minutes, counts stuck at 0, raw i18n keys). Mitigation: run on MongoDB (snap: `snap set wekan database=mongodb`) or migrate text data across, and check for a migration/repair still running.',
|
|
};
|
|
}
|
|
|
|
Meteor.methods({
|
|
// The full Problems "Status" overview: everything in progress + problems found.
|
|
async systemStatusReport() {
|
|
await requireAdmin();
|
|
const [overview, loginProblems] = await Promise.all([
|
|
getProblemsOverview(),
|
|
getLoginProblems(),
|
|
]);
|
|
return { overview, loginProblems };
|
|
},
|
|
|
|
// Just the in-progress migrations/repairs (cheap; polled by the Status page).
|
|
async migrationsInProgress() {
|
|
await requireAdmin();
|
|
return getInProgress();
|
|
},
|
|
|
|
// Detail for one problem area (currently 'cpu'); mirrors the snap sub-command.
|
|
async problemDetailReport(area) {
|
|
await requireAdmin();
|
|
if (area === 'cpu') return cpuDetail();
|
|
if (area === 'login') return { area: 'login', checks: await getLoginProblems() };
|
|
if (area === 'status' || !area) return getProblemsOverview();
|
|
throw new Meteor.Error('unknown-area', `Unknown problem area: ${area}`);
|
|
},
|
|
});
|