b2in/app/Services/Monitoring/HealthProbe.php

<?php

namespace App\Services\Monitoring;

use Illuminate\Support\Carbon;
use Illuminate\Support\Facades\Cache;
use Illuminate\Support\Facades\DB;
use Illuminate\Support\Str;
use Throwable;

/**
 * Die Prüfungen, die ein externer Monitor jede Minute abfragt
 *: Datenbank, Cache, Queue-Rückstau,
 * Scheduler-Herzschlag, Plattenplatz. Bewusst billig — keine Zählungen über
 * große Tabellen, damit `/health` selbst keine Last erzeugt.
 *
 * Ein Admin-Systemstatus kann `scheduler()` und `disk()` mitbenutzen.
 */
class HealthProbe
{
    public const StatusOk = 'ok';

    public const StatusWarn = 'warn';

    public const StatusCritical = 'critical';

    /**
     * Datei statt Datenbank/Cache: übersteht `cache:clear`, braucht keine
     * Migration. Bei mehreren App-Servern stattdessen eine DB-Zeile nehmen.
     */
    public static function heartbeatPath(): string
    {
        return (string) (config('monitoring.scheduler.heartbeat_path') ?: storage_path('framework/scheduler-heartbeat'));
    }

    public function recordHeartbeat(): void
    {
        file_put_contents(self::heartbeatPath(), now()->toIso8601String(), LOCK_EX);
    }

    public function lastHeartbeat(): ?Carbon
    {
        $value = @file_get_contents(self::heartbeatPath());

        return is_string($value) && trim($value) !== '' ? Carbon::parse(trim($value)) : null;
    }

    /**
     * @return list<array{key: string, label: string, status: string, detail: string}>
     */
    public function checks(): array
    {
        return [
            $this->database(),
            $this->cache(),
            $this->queue(),
            $this->scheduler(),
            $this->disk(),
        ];
    }

    /**
     * @param  list<array{status: string}>  $checks
     */
    public static function worstStatus(array $checks): string
    {
        $statuses = array_column($checks, 'status');

        return match (true) {
            in_array(self::StatusCritical, $statuses, true) => self::StatusCritical,
            in_array(self::StatusWarn, $statuses, true) => self::StatusWarn,
            default => self::StatusOk,
        };
    }

    /**
     * @return array{key: string, label: string, status: string, detail: string}
     */
    public function scheduler(): array
    {
        $lastBeat = $this->lastHeartbeat();
        $warnMinutes = (int) config('monitoring.scheduler.heartbeat_warn_minutes');
        $criticalMinutes = (int) config('monitoring.scheduler.heartbeat_critical_minutes');
        $minutesAgo = $lastBeat !== null ? (int) $lastBeat->diffInMinutes(now(), absolute: true) : null;

        return $this->check(
            'scheduler',
            'Scheduler',
            match (true) {
                $minutesAgo === null, $minutesAgo >= $criticalMinutes => self::StatusCritical,
                $minutesAgo >= $warnMinutes => self::StatusWarn,
                default => self::StatusOk,
            },
            $lastBeat === null
                ? 'Noch kein Herzschlag — läuft `schedule:run` per Cron (bzw. `schedule:work`)?'
                : 'Letzter Herzschlag '.$lastBeat->format('d.m.Y H:i:s').' (vor '.$minutesAgo.' Min.).',
        );
    }

    /**
     * @return array{key: string, label: string, status: string, detail: string}
     */
    public function disk(): array
    {
        $path = storage_path();
        $free = @disk_free_space($path);
        $total = @disk_total_space($path);

        if ($free === false || $total === false || $total <= 0) {
            return $this->check('disk', 'Plattenplatz', self::StatusWarn, 'Plattenplatz nicht ermittelbar.');
        }

        $freePercent = round($free / $total * 100, 1);
        $minPercent = (float) config('monitoring.health.disk_min_free_percent');

        return $this->check(
            'disk',
            'Plattenplatz',
            match (true) {
                $freePercent < $minPercent => self::StatusCritical,
                $freePercent < $minPercent * 2 => self::StatusWarn,
                default => self::StatusOk,
            },
            sprintf('%s %% frei (%s GB von %s GB).', $freePercent, round($free / 1024 ** 3, 1), round($total / 1024 ** 3, 1)),
        );
    }

    /**
     * @return array{key: string, label: string, status: string, detail: string}
     */
    private function database(): array
    {
        try {
            DB::select('select 1');

            return $this->check('database', 'Datenbank', self::StatusOk, 'Verbindung steht.');
        } catch (Throwable $exception) {
            return $this->check('database', 'Datenbank', self::StatusCritical, 'Keine Verbindung: '.Str::limit($exception->getMessage(), 120));
        }
    }

    /**
     * @return array{key: string, label: string, status: string, detail: string}
     */
    private function cache(): array
    {
        try {
            $value = Str::random(8);
            Cache::put('monitoring:health-probe', $value, 60);

            return Cache::get('monitoring:health-probe') === $value
                ? $this->check('cache', 'Cache', self::StatusOk, 'Schreiben und Lesen funktionieren.')
                : $this->check('cache', 'Cache', self::StatusCritical, 'Geschriebener Wert kommt nicht zurück.');
        } catch (Throwable $exception) {
            return $this->check('cache', 'Cache', self::StatusCritical, 'Nicht erreichbar: '.Str::limit($exception->getMessage(), 120));
        }
    }

    /**
     * @return array{key: string, label: string, status: string, detail: string}
     */
    private function queue(): array
    {
        if (config('queue.default') !== 'database') {
            return $this->check('queue', 'Queue', self::StatusOk, 'Treiber '.config('queue.default').' — Rückstau hier nicht prüfbar.');
        }

        try {
            $now = now()->getTimestamp();
            $oldestAvailable = DB::table('jobs')
                ->whereNull('reserved_at')
                ->where('available_at', '<=', $now)
                ->min('available_at');
        } catch (Throwable $exception) {
            return $this->check('queue', 'Queue', self::StatusCritical, 'Jobs-Tabelle nicht lesbar: '.Str::limit($exception->getMessage(), 120));
        }

        $waitingSeconds = $oldestAvailable !== null ? max(0, $now - (int) $oldestAvailable) : 0;
        $criticalSeconds = (int) config('monitoring.health.queue_backlog_critical_seconds');

        return $this->check(
            'queue',
            'Queue',
            $waitingSeconds >= $criticalSeconds ? self::StatusCritical : self::StatusOk,
            $oldestAvailable === null
                ? 'Kein wartender Job.'
                : 'Ältester wartender Job seit '.$waitingSeconds.' s.'.($waitingSeconds >= $criticalSeconds ? ' Worker gestoppt?' : ''),
        );
    }

    /**
     * @return array{key: string, label: string, status: string, detail: string}
     */
    private function check(string $key, string $label, string $status, string $detail): array
    {
        return ['key' => $key, 'label' => $label, 'status' => $status, 'detail' => $detail];
    }
}