- Backups: a guest whose newest backup is older than its limit is an alert (backup kind), in the daily backup message, the digest and /metrics (homelab_backup_guests, ..._last_age_seconds) - Per-server thresholds (servers.thresholds, migration 0030): offline minutes, disk percent, forecast window, backup age, and per-disk limits or "leave alone"; applied everywhere the global ones were; saving clears the alerts cache - Update runs (update_runs, migration 0031): Update... on the Updates page puts the server under maintenance, runs a Semaphore playbook limited to it, waits for the host to report, and reports what is left and whether a restart is due; poller survives restarts - Notification toggle for update-run results; tests and docs Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
89 lines
3.7 KiB
TypeScript
89 lines
3.7 KiB
TypeScript
import { evaluateHealth, type Thresholds } from "./healthMonitor.js";
|
|
import { parseThresholds } from "./serverThresholds.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
|
|
/** This server's own thresholds, as stored. */
|
|
thresholds?: string | null;
|
|
}
|
|
|
|
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), thresholds: parseThresholds(r.thresholds) })),
|
|
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 },
|
|
};
|
|
}
|