Add a Servers widget to the dashboard
A Servers card in the dashboard's Overview row, in the same shape as the DNS and Secrets cards: a status badge (N offline / N disks nearly full / All online / No agent data / Not configured), total, online and offline counts, an online/offline/no-data bar, and the details that matter -- which servers are offline and for how long (the first three, linking to their pages), which disks are at or above the usage threshold, and a Linux/Windows split when there are Windows machines. The numbers come from a new GET /api/servers/summary, computed on the server with the health monitor's own evaluateHealth. That means "offline" and "disk full" are decided by exactly the rules the alerts use, so the widget can't say a server is fine while an alert says it isn't, and it follows the thresholds set in Settings, which viewers can't read themselves and so couldn't have applied client-side. Servers under a maintenance window are marked as such. A server that has never reported (no agent, or tracked only through Proxmox) counts as "no data" rather than offline, an offline server's stale disk figure isn't reported, and a garbled report doesn't blank the widget. Readable by every signed-in user, like the dashboard itself. Verified with 23 backend checks (offline/online/no-data classification including the bare SQLite timestamp format, ordering, colons in Windows mounts, threshold changes, maintenance flags, agreement with the alert path's own offline and disk sets, empty and garbled inputs, and the route as a viewer following Settings) and in a browser against the real router across five states: problems, disks only, all healthy, no data, and empty. Real dev database mtime untouched. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
1 parent
fea20456e4
commit
91796a3c3a
5 files changed
+223
-1
No files matched your search
@@ -11,6 +11,9 @@ import { loadIntegrationConfig } from "../integrations/loadIntegration.js";
|
||||
import { createProxmoxAdapter, type ProxmoxGuestType } from "../integrations/proxmox/adapter.js";
|
||||
import { serverPortsRouter } from "./serverPorts.js";
|
||||
import { InvalidTagError, normalizeTags, parseTags } from "../services/serverTags.js";
|
||||
import { buildServerSummary } from "../services/serverSummary.js";
|
||||
import { activeSubjects } from "../services/maintenance.js";
|
||||
import { getSettings } from "../services/settingsStore.js";
|
||||
|
||||
export const serversRouter = Router();
|
||||
|
||||
@@ -157,6 +160,16 @@ serversRouter.patch("/:id", requireRole("admin"), asyncHandler(async (req, res)
|
||||
res.json({ server: serverOut });
|
||||
}));
|
||||
|
||||
// For the dashboard widget. Computed here, with the health monitor's own rules and the thresholds from Settings
|
||||
// (which viewers can't read), so the widget and the alerts always agree about what "offline" and "full" mean.
|
||||
serversRouter.get("/summary", asyncHandler(async (_req, res) => {
|
||||
const rows = await db
|
||||
.select({ id: servers.id, name: servers.name, osType: servers.osType, lastSeenAt: servers.lastSeenAt, disks: servers.disks })
|
||||
.from(servers);
|
||||
const { healthChecks } = await getSettings();
|
||||
res.json(buildServerSummary(rows, healthChecks, Date.now(), await activeSubjects()));
|
||||
}));
|
||||
|
||||
serversRouter.get("/:id/detail", asyncHandler(async (req, res) => {
|
||||
const id = Number(req.params.id);
|
||||
if (!Number.isInteger(id)) return res.status(400).json({ error: "invalid_id" });
|
||||
|
||||
@@ -0,0 +1,85 @@
|
||||
import { evaluateHealth, type Thresholds } from "./healthMonitor.js";
|
||||
|
||||
/** The columns of a server row the summary reads. */
|
||||
export interface SummaryRow {
|
||||
id: number;
|
||||
name: string;
|
||||
osType: string;
|
||||
lastSeenAt: string | null;
|
||||
disks: string | null; // JSON, as the agent's report is stored
|
||||
}
|
||||
|
||||
export interface ServerSummary {
|
||||
total: number;
|
||||
/** Reported within the "server offline after" threshold. */
|
||||
online: number;
|
||||
/** Has reported before, but not recently enough. */
|
||||
offline: { id: number; name: string; lastSeenAt: string; inMaintenance: boolean }[];
|
||||
/** Never reported: no agent, or not yet — a server tracked only through Proxmox lands here too. */
|
||||
noData: number;
|
||||
byOs: { linux: number; windows: number };
|
||||
/** Reporting servers with a disk at or above the usage threshold. */
|
||||
fullDisks: { id: number; name: string; mount: string; percent: number }[];
|
||||
thresholds: { offlineMinutes: number; diskPercent: number };
|
||||
}
|
||||
|
||||
function parseDisks(text: string | null): { mount: string; sizeBytes: number; usedBytes: number }[] {
|
||||
if (!text) return [];
|
||||
try {
|
||||
const value = JSON.parse(text);
|
||||
return Array.isArray(value) ? value : [];
|
||||
} catch {
|
||||
return []; // a garbled report shouldn't blank the whole widget
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* What the dashboard's Servers widget shows. "Offline" and "disk full" are decided by the same function the alerts
|
||||
* use (evaluateHealth), so the widget can never say a server is fine while an alert says it isn't, or the reverse —
|
||||
* and it follows the thresholds set in Settings, which viewers can't read themselves.
|
||||
*/
|
||||
export function buildServerSummary(rows: SummaryRow[], thresholds: Thresholds, now: number, silencedSubjects: Set<string> = new Set()): ServerSummary {
|
||||
const snapshot = {
|
||||
servers: rows.map((r) => ({ id: r.id, name: r.name, lastSeenAt: r.lastSeenAt, disks: parseDisks(r.disks) })),
|
||||
proxmox: [],
|
||||
synology: [],
|
||||
};
|
||||
const conditions = evaluateHealth(snapshot, thresholds, now);
|
||||
const byId = new Map(rows.map((r) => [r.id, r]));
|
||||
|
||||
const offlineIds = new Set<number>();
|
||||
const fullDisks: ServerSummary["fullDisks"] = [];
|
||||
for (const c of conditions) {
|
||||
let m = /^offline:server:(\d+)$/.exec(c.key);
|
||||
if (m) {
|
||||
offlineIds.add(Number(m[1]));
|
||||
continue;
|
||||
}
|
||||
// The mount can contain a colon ("C:"), so take everything after the id.
|
||||
m = /^disk:server:(\d+):(.*)$/.exec(c.key);
|
||||
if (m) {
|
||||
const row = byId.get(Number(m[1]));
|
||||
const disk = row ? parseDisks(row.disks).find((d) => d.mount === m![2]) : undefined;
|
||||
if (row && disk && disk.sizeBytes > 0) {
|
||||
fullDisks.push({ id: row.id, name: row.name, mount: disk.mount, percent: Math.round((disk.usedBytes / disk.sizeBytes) * 100) });
|
||||
}
|
||||
}
|
||||
}
|
||||
fullDisks.sort((a, b) => b.percent - a.percent || a.name.localeCompare(b.name));
|
||||
|
||||
const offline = rows
|
||||
.filter((r) => offlineIds.has(r.id) && r.lastSeenAt)
|
||||
.map((r) => ({ id: r.id, name: r.name, lastSeenAt: r.lastSeenAt!, inMaintenance: silencedSubjects.has(`server:${r.id}`) }))
|
||||
.sort((a, b) => a.lastSeenAt.localeCompare(b.lastSeenAt)); // longest silent first
|
||||
|
||||
const noData = rows.filter((r) => !r.lastSeenAt).length;
|
||||
return {
|
||||
total: rows.length,
|
||||
online: rows.length - noData - offline.length,
|
||||
offline,
|
||||
noData,
|
||||
byOs: { linux: rows.filter((r) => r.osType !== "windows").length, windows: rows.filter((r) => r.osType === "windows").length },
|
||||
fullDisks,
|
||||
thresholds: { offlineMinutes: thresholds.serverOfflineMinutes, diskPercent: thresholds.diskUsagePercent },
|
||||
};
|
||||
}
|
||||
Reference in new issue
Block a user