transceiver-db/scripts/fleet-heartbeat.mjs

38 lines
1.4 KiB
JavaScript

/**
* Pi/host fleet heartbeat: self-report local pm2 process health to Postgres so a
* central detector on Erik can catch crash-loops (restart_time velocity + near-0
* uptime) and stale/dead hosts — which a naive "pm2 status == online" check misses.
* Runs on each Pi via cron (every 5 min). DB via the local tunnel (127.0.0.1:5433).
*/
import { execFileSync } from "node:child_process";
import os from "node:os";
import { config } from "dotenv";
import pg from "pg";
config({ path: new URL("../.env", import.meta.url) }); // ~/tip/.env
const host = os.hostname();
let procs = [];
try { procs = JSON.parse(execFileSync("pm2", ["jlist"], { encoding: "utf8", maxBuffer: 8 * 1024 * 1024 })); }
catch { process.exit(0); }
const pool = new pg.Pool({
host: "127.0.0.1", port: 5433,
user: process.env.POSTGRES_USER || "tip",
database: process.env.POSTGRES_DB || "transceiver_db",
password: process.env.POSTGRES_PASSWORD,
max: 1, connectionTimeoutMillis: 8000, statement_timeout: 8000,
});
try {
for (const p of procs) {
const e = p.pm2_env || {};
const uptimeS = Math.round((Date.now() - (e.pm_uptime || Date.now())) / 1000);
await pool.query(
"insert into fleet_health(host,pm_name,status,restart_time,uptime_s) values($1,$2,$3,$4,$5)",
[host, p.name, e.status || null, e.restart_time ?? 0, uptimeS],
);
}
} catch { /* heartbeat is best-effort; never crash the host */ }
finally { await pool.end().catch(() => {}); }