feat(monitoring): Fleet-Crash-Loop-Watchdog — Pi-Heartbeat (fleet_health) + Erik-Detector (v_fleet_health) schließt den Self-Healing-Blindspot (Crash-Loop tarnt sich als online)
This commit is contained in:
parent
4806cdfd1c
commit
8d11a4d24d
27
scripts/fleet-health-monitor.sh
Normal file
27
scripts/fleet-health-monitor.sh
Normal file
@ -0,0 +1,27 @@
|
||||
#!/bin/bash
|
||||
# Fleet crash-loop / dead-worker detector (Erik). Reads v_fleet_health (fed by the
|
||||
# Pi heartbeats in fleet_health) and alerts on verdict<>ok. Closes the blind spot
|
||||
# where a crash-looping pm2 process reports "online" and a naive liveness check
|
||||
# misses it — the 3-Pi worker fleet was dead ~months (2026-07) exactly this way.
|
||||
# Cron: */10. Alert = log + optional ntfy push (FLEET_NTFY_URL).
|
||||
set -uo pipefail
|
||||
LOG=/opt/tip/logs/fleet-health.log
|
||||
mkdir -p "$(dirname "$LOG")"
|
||||
TS=$(date '+%Y-%m-%d %H:%M:%S')
|
||||
|
||||
# shellcheck disable=SC1091
|
||||
source /opt/tip/.env 2>/dev/null || true
|
||||
Q="select host||' '||pm_name||' -> '||verdict||' (restart_delta='||restart_delta||', uptime='||uptime_s||'s, age='||age_s||'s)' from v_fleet_health where verdict <> 'ok' order by host"
|
||||
ALERTS=$(docker exec -e PGPASSWORD="${POSTGRES_PASSWORD:-}" tip-postgres psql -U tip -d transceiver_db -tA -c "$Q" 2>/dev/null)
|
||||
|
||||
if [ -n "$ALERTS" ]; then
|
||||
N=$(printf '%s\n' "$ALERTS" | grep -c .)
|
||||
echo "[$TS] FLEET ALERT ($N):" >> "$LOG"
|
||||
printf '%s\n' "$ALERTS" | sed 's/^/[ ] /' >> "$LOG"
|
||||
# best-effort push (set FLEET_NTFY_URL in /opt/tip/.env to enable, e.g. https://ntfy.sh/tip-fleet)
|
||||
if [ -n "${FLEET_NTFY_URL:-}" ]; then
|
||||
printf 'TIP fleet alert (%s):\n%s\n' "$N" "$ALERTS" | curl -s -m 8 -H "Title: TIP fleet crash-loop/dead" -d @- "$FLEET_NTFY_URL" >/dev/null 2>&1 || true
|
||||
fi
|
||||
else
|
||||
echo "[$TS] fleet ok" >> "$LOG"
|
||||
fi
|
||||
37
scripts/fleet-heartbeat.mjs
Normal file
37
scripts/fleet-heartbeat.mjs
Normal file
@ -0,0 +1,37 @@
|
||||
/**
|
||||
* 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(() => {}); }
|
||||
Loading…
x
Reference in New Issue
Block a user