2024-10-14 10:07:37 +00:00
|
|
|
<?php
|
|
|
|
|
|
|
|
|
|
namespace App\Jobs;
|
|
|
|
|
|
2024-10-14 15:54:29 +00:00
|
|
|
use App\Actions\Database\StartDatabaseProxy;
|
2024-10-14 17:45:03 +00:00
|
|
|
use App\Actions\Database\StopDatabaseProxy;
|
2024-10-15 11:39:19 +00:00
|
|
|
use App\Actions\Proxy\CheckProxy;
|
2024-10-14 11:32:36 +00:00
|
|
|
use App\Actions\Proxy\StartProxy;
|
2024-10-30 13:54:27 +00:00
|
|
|
use App\Actions\Server\StartLogDrain;
|
2024-10-14 15:54:29 +00:00
|
|
|
use App\Actions\Shared\ComplexStatusCheck;
|
2024-10-14 11:32:36 +00:00
|
|
|
use App\Models\Application;
|
2024-10-14 10:07:37 +00:00
|
|
|
use App\Models\Server;
|
2024-10-14 15:54:29 +00:00
|
|
|
use App\Models\ServiceApplication;
|
|
|
|
|
use App\Models\ServiceDatabase;
|
2024-10-22 09:42:24 +00:00
|
|
|
use App\Notifications\Container\ContainerRestarted;
|
2024-10-14 10:07:37 +00:00
|
|
|
use Illuminate\Bus\Queueable;
|
2024-10-24 13:16:00 +00:00
|
|
|
use Illuminate\Contracts\Queue\ShouldBeEncrypted;
|
2024-10-14 10:07:37 +00:00
|
|
|
use Illuminate\Contracts\Queue\ShouldQueue;
|
|
|
|
|
use Illuminate\Foundation\Bus\Dispatchable;
|
|
|
|
|
use Illuminate\Queue\InteractsWithQueue;
|
2025-01-10 10:54:45 +00:00
|
|
|
use Illuminate\Queue\Middleware\WithoutOverlapping;
|
2024-10-14 10:07:37 +00:00
|
|
|
use Illuminate\Queue\SerializesModels;
|
2024-10-14 11:32:36 +00:00
|
|
|
use Illuminate\Support\Collection;
|
debug: add comprehensive status change logging
Added detailed debug logging to all status update paths to help
diagnose why "unhealthy" status appears in the UI.
## Logging Added
### 1. PushServerUpdateJob (Sentinel updates)
**Location**: Lines 303-315
**Logs**: Status changes from Sentinel push updates
**Data tracked**:
- Old vs new status
- Container statuses that led to aggregation
- Status flags (hasRunning, hasUnhealthy, hasUnknown)
### 2. GetContainersStatus (SSH updates)
**Location**: Lines 441-449, 346-354, 358-365
**Logs**: Status changes from SSH-based checks
**Scenarios**:
- Normal status aggregation
- Recently restarted containers (kept as degraded)
- Applications not running (set to exited)
**Data tracked**:
- Old vs new status
- Container statuses
- Restart count and timing
- Whether containers exist
### 3. Application Model Status Accessor
**Location**: Lines 706-712, 726-732
**Logs**: When status is set without explicit health information
**Issue**: Highlights cases where health defaults to "unhealthy"
**Data tracked**:
- Raw value passed to setter
- Final result after default applied
## How to Use
### Enable Debug Logging
Edit `.env` or `config/logging.php` to set log level to debug:
```
LOG_LEVEL=debug
```
### Monitor Logs
```bash
tail -f storage/logs/laravel.log | grep STATUS-DEBUG
```
### Log Format
All logs use `[STATUS-DEBUG]` prefix for easy filtering:
```
[2025-11-19 13:00:00] local.DEBUG: [STATUS-DEBUG] Sentinel status change
{
"source": "PushServerUpdateJob",
"app_id": 123,
"app_name": "my-app",
"old_status": "running:unknown",
"new_status": "running:healthy",
"container_statuses": [...],
"flags": {...}
}
```
## What to Look For
1. **Default to unhealthy**: Check Application model accessor logs
2. **Status flipping**: Compare timestamps between Sentinel and SSH updates
3. **Incorrect aggregation**: Check flags and container_statuses
4. **Stale database values**: Check if old_status persists across multiple logs
## Next Steps
After gathering logs, we can:
1. Identify the exact source of "unhealthy" status
2. Determine if it's a default issue, aggregation bug, or timing problem
3. Apply targeted fix based on evidence
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-19 12:52:08 +00:00
|
|
|
use Illuminate\Support\Facades\Log;
|
2025-07-12 12:44:32 +00:00
|
|
|
use Laravel\Horizon\Contracts\Silenced;
|
2024-10-14 10:07:37 +00:00
|
|
|
|
2025-07-12 12:44:32 +00:00
|
|
|
class PushServerUpdateJob implements ShouldBeEncrypted, ShouldQueue, Silenced
|
2024-10-14 10:07:37 +00:00
|
|
|
{
|
|
|
|
|
use Dispatchable, InteractsWithQueue, Queueable, SerializesModels;
|
|
|
|
|
|
|
|
|
|
public $tries = 1;
|
|
|
|
|
|
2024-10-14 15:54:29 +00:00
|
|
|
public $timeout = 30;
|
|
|
|
|
|
|
|
|
|
public Collection $containers;
|
|
|
|
|
|
2024-10-14 20:53:16 +00:00
|
|
|
public Collection $applications;
|
|
|
|
|
|
|
|
|
|
public Collection $previews;
|
|
|
|
|
|
|
|
|
|
public Collection $databases;
|
|
|
|
|
|
|
|
|
|
public Collection $services;
|
|
|
|
|
|
2024-10-14 15:54:29 +00:00
|
|
|
public Collection $allApplicationIds;
|
|
|
|
|
|
|
|
|
|
public Collection $allDatabaseUuids;
|
|
|
|
|
|
2024-10-15 11:39:19 +00:00
|
|
|
public Collection $allTcpProxyUuids;
|
|
|
|
|
|
2024-10-14 15:54:29 +00:00
|
|
|
public Collection $allServiceApplicationIds;
|
|
|
|
|
|
|
|
|
|
public Collection $allApplicationPreviewsIds;
|
|
|
|
|
|
|
|
|
|
public Collection $allServiceDatabaseIds;
|
|
|
|
|
|
|
|
|
|
public Collection $allApplicationsWithAdditionalServers;
|
|
|
|
|
|
|
|
|
|
public Collection $foundApplicationIds;
|
|
|
|
|
|
|
|
|
|
public Collection $foundDatabaseUuids;
|
|
|
|
|
|
|
|
|
|
public Collection $foundServiceApplicationIds;
|
|
|
|
|
|
|
|
|
|
public Collection $foundServiceDatabaseIds;
|
|
|
|
|
|
|
|
|
|
public Collection $foundApplicationPreviewsIds;
|
|
|
|
|
|
2025-09-13 18:32:15 +00:00
|
|
|
public Collection $applicationContainerStatuses;
|
|
|
|
|
|
2024-10-14 15:54:29 +00:00
|
|
|
public bool $foundProxy = false;
|
2024-10-15 15:03:50 +00:00
|
|
|
|
2024-10-15 11:39:19 +00:00
|
|
|
public bool $foundLogDrainContainer = false;
|
2024-10-14 10:07:37 +00:00
|
|
|
|
2025-01-10 10:54:45 +00:00
|
|
|
public function middleware(): array
|
|
|
|
|
{
|
2025-07-01 08:50:27 +00:00
|
|
|
return [(new WithoutOverlapping('push-server-update-'.$this->server->uuid))->expireAfter(30)->dontRelease()];
|
2025-01-10 10:54:45 +00:00
|
|
|
}
|
|
|
|
|
|
2024-10-14 10:07:37 +00:00
|
|
|
public function backoff(): int
|
|
|
|
|
{
|
|
|
|
|
return isDev() ? 1 : 3;
|
|
|
|
|
}
|
|
|
|
|
|
2024-10-14 11:32:36 +00:00
|
|
|
public function __construct(public Server $server, public $data)
|
|
|
|
|
{
|
2024-10-14 15:54:29 +00:00
|
|
|
$this->containers = collect();
|
|
|
|
|
$this->foundApplicationIds = collect();
|
|
|
|
|
$this->foundDatabaseUuids = collect();
|
|
|
|
|
$this->foundServiceApplicationIds = collect();
|
|
|
|
|
$this->foundApplicationPreviewsIds = collect();
|
|
|
|
|
$this->foundServiceDatabaseIds = collect();
|
2025-09-13 18:32:15 +00:00
|
|
|
$this->applicationContainerStatuses = collect();
|
2024-10-14 15:54:29 +00:00
|
|
|
$this->allApplicationIds = collect();
|
|
|
|
|
$this->allDatabaseUuids = collect();
|
|
|
|
|
$this->allTcpProxyUuids = collect();
|
|
|
|
|
$this->allServiceApplicationIds = collect();
|
|
|
|
|
$this->allServiceDatabaseIds = collect();
|
2024-10-14 11:32:36 +00:00
|
|
|
}
|
2024-10-14 10:07:37 +00:00
|
|
|
|
|
|
|
|
public function handle()
|
|
|
|
|
{
|
2024-10-22 09:29:43 +00:00
|
|
|
// TODO: Swarm is not supported yet
|
2024-10-28 13:37:00 +00:00
|
|
|
if (! $this->data) {
|
|
|
|
|
throw new \Exception('No data provided');
|
|
|
|
|
}
|
|
|
|
|
$data = collect($this->data);
|
2024-10-15 11:39:19 +00:00
|
|
|
|
2024-10-28 13:37:00 +00:00
|
|
|
$this->server->sentinelHeartbeat();
|
2024-10-15 11:39:19 +00:00
|
|
|
|
2024-10-28 13:37:00 +00:00
|
|
|
$this->containers = collect(data_get($data, 'containers'));
|
2024-10-22 12:01:36 +00:00
|
|
|
|
2024-10-28 13:37:00 +00:00
|
|
|
$filesystemUsageRoot = data_get($data, 'filesystem_usage_root.used_percentage');
|
|
|
|
|
ServerStorageCheckJob::dispatch($this->server, $filesystemUsageRoot);
|
2024-10-22 12:01:36 +00:00
|
|
|
|
2024-10-28 13:37:00 +00:00
|
|
|
if ($this->containers->isEmpty()) {
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
$this->applications = $this->server->applications();
|
|
|
|
|
$this->databases = $this->server->databases();
|
|
|
|
|
$this->previews = $this->server->previews();
|
|
|
|
|
$this->services = $this->server->services()->get();
|
|
|
|
|
$this->allApplicationIds = $this->applications->filter(function ($application) {
|
|
|
|
|
return $application->additional_servers->count() === 0;
|
|
|
|
|
})->pluck('id');
|
|
|
|
|
$this->allApplicationsWithAdditionalServers = $this->applications->filter(function ($application) {
|
|
|
|
|
return $application->additional_servers->count() > 0;
|
|
|
|
|
});
|
2025-06-04 08:03:36 +00:00
|
|
|
$this->allApplicationPreviewsIds = $this->previews->map(function ($preview) {
|
|
|
|
|
return $preview->application_id.':'.$preview->pull_request_id;
|
|
|
|
|
});
|
2024-10-28 13:37:00 +00:00
|
|
|
$this->allDatabaseUuids = $this->databases->pluck('uuid');
|
|
|
|
|
$this->allTcpProxyUuids = $this->databases->where('is_public', true)->pluck('uuid');
|
|
|
|
|
$this->services->each(function ($service) {
|
|
|
|
|
$service->applications()->pluck('id')->each(function ($applicationId) {
|
|
|
|
|
$this->allServiceApplicationIds->push($applicationId);
|
2024-10-14 20:53:16 +00:00
|
|
|
});
|
2024-10-28 13:37:00 +00:00
|
|
|
$service->databases()->pluck('id')->each(function ($databaseId) {
|
|
|
|
|
$this->allServiceDatabaseIds->push($databaseId);
|
2024-10-14 15:54:29 +00:00
|
|
|
});
|
2024-10-28 13:37:00 +00:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
foreach ($this->containers as $container) {
|
|
|
|
|
$containerStatus = data_get($container, 'state', 'exited');
|
|
|
|
|
$containerHealth = data_get($container, 'health_status', 'unhealthy');
|
|
|
|
|
$containerStatus = "$containerStatus ($containerHealth)";
|
|
|
|
|
$labels = collect(data_get($container, 'labels'));
|
|
|
|
|
$coolify_managed = $labels->has('coolify.managed');
|
|
|
|
|
if ($coolify_managed) {
|
|
|
|
|
$name = data_get($container, 'name');
|
|
|
|
|
if ($name === 'coolify-log-drain' && $this->isRunning($containerStatus)) {
|
|
|
|
|
$this->foundLogDrainContainer = true;
|
|
|
|
|
}
|
|
|
|
|
if ($labels->has('coolify.applicationId')) {
|
|
|
|
|
$applicationId = $labels->get('coolify.applicationId');
|
2025-06-04 08:03:36 +00:00
|
|
|
$pullRequestId = $labels->get('coolify.pullRequestId', '0');
|
2024-10-28 13:37:00 +00:00
|
|
|
try {
|
|
|
|
|
if ($pullRequestId === '0') {
|
|
|
|
|
if ($this->allApplicationIds->contains($applicationId) && $this->isRunning($containerStatus)) {
|
|
|
|
|
$this->foundApplicationIds->push($applicationId);
|
2024-10-14 15:54:29 +00:00
|
|
|
}
|
2025-09-13 18:32:15 +00:00
|
|
|
// Store container status for aggregation
|
|
|
|
|
if (! $this->applicationContainerStatuses->has($applicationId)) {
|
|
|
|
|
$this->applicationContainerStatuses->put($applicationId, collect());
|
|
|
|
|
}
|
|
|
|
|
$containerName = $labels->get('com.docker.compose.service');
|
|
|
|
|
if ($containerName) {
|
|
|
|
|
$this->applicationContainerStatuses->get($applicationId)->put($containerName, $containerStatus);
|
|
|
|
|
}
|
2024-10-28 13:37:00 +00:00
|
|
|
} else {
|
2025-06-04 08:03:36 +00:00
|
|
|
$previewKey = $applicationId.':'.$pullRequestId;
|
|
|
|
|
if ($this->allApplicationPreviewsIds->contains($previewKey) && $this->isRunning($containerStatus)) {
|
|
|
|
|
$this->foundApplicationPreviewsIds->push($previewKey);
|
2024-10-28 13:37:00 +00:00
|
|
|
}
|
2025-06-04 08:03:36 +00:00
|
|
|
$this->updateApplicationPreviewStatus($applicationId, $pullRequestId, $containerStatus);
|
2024-10-14 16:04:36 +00:00
|
|
|
}
|
2024-10-28 13:37:00 +00:00
|
|
|
} catch (\Exception $e) {
|
|
|
|
|
}
|
|
|
|
|
} elseif ($labels->has('coolify.serviceId')) {
|
|
|
|
|
$serviceId = $labels->get('coolify.serviceId');
|
|
|
|
|
$subType = $labels->get('coolify.service.subType');
|
|
|
|
|
$subId = $labels->get('coolify.service.subId');
|
|
|
|
|
if ($subType === 'application' && $this->isRunning($containerStatus)) {
|
|
|
|
|
$this->foundServiceApplicationIds->push($subId);
|
|
|
|
|
$this->updateServiceSubStatus($serviceId, $subType, $subId, $containerStatus);
|
|
|
|
|
} elseif ($subType === 'database' && $this->isRunning($containerStatus)) {
|
|
|
|
|
$this->foundServiceDatabaseIds->push($subId);
|
|
|
|
|
$this->updateServiceSubStatus($serviceId, $subType, $subId, $containerStatus);
|
|
|
|
|
}
|
|
|
|
|
} else {
|
|
|
|
|
$uuid = $labels->get('com.docker.compose.service');
|
|
|
|
|
$type = $labels->get('coolify.type');
|
|
|
|
|
if ($name === 'coolify-proxy' && $this->isRunning($containerStatus)) {
|
|
|
|
|
$this->foundProxy = true;
|
|
|
|
|
} elseif ($type === 'service' && $this->isRunning($containerStatus)) {
|
2024-10-14 11:32:36 +00:00
|
|
|
} else {
|
2024-10-28 13:37:00 +00:00
|
|
|
if ($this->allDatabaseUuids->contains($uuid) && $this->isRunning($containerStatus)) {
|
|
|
|
|
$this->foundDatabaseUuids->push($uuid);
|
|
|
|
|
if ($this->allTcpProxyUuids->contains($uuid) && $this->isRunning($containerStatus)) {
|
|
|
|
|
$this->updateDatabaseStatus($uuid, $containerStatus, tcpProxy: true);
|
|
|
|
|
} else {
|
|
|
|
|
$this->updateDatabaseStatus($uuid, $containerStatus, tcpProxy: false);
|
2024-10-14 15:54:29 +00:00
|
|
|
}
|
|
|
|
|
}
|
2024-10-14 11:32:36 +00:00
|
|
|
}
|
|
|
|
|
}
|
2024-10-14 10:07:37 +00:00
|
|
|
}
|
2024-10-28 13:37:00 +00:00
|
|
|
}
|
2024-10-14 11:32:36 +00:00
|
|
|
|
2024-10-28 13:37:00 +00:00
|
|
|
$this->updateProxyStatus();
|
2024-10-15 11:39:19 +00:00
|
|
|
|
2024-10-28 13:37:00 +00:00
|
|
|
$this->updateNotFoundApplicationStatus();
|
|
|
|
|
$this->updateNotFoundApplicationPreviewStatus();
|
|
|
|
|
$this->updateNotFoundDatabaseStatus();
|
|
|
|
|
$this->updateNotFoundServiceStatus();
|
2024-10-15 11:39:19 +00:00
|
|
|
|
2024-10-28 13:37:00 +00:00
|
|
|
$this->updateAdditionalServersStatus();
|
2024-10-14 15:54:29 +00:00
|
|
|
|
2025-09-13 18:32:15 +00:00
|
|
|
// Aggregate multi-container application statuses
|
|
|
|
|
$this->aggregateMultiContainerStatuses();
|
|
|
|
|
|
2024-10-28 13:37:00 +00:00
|
|
|
$this->checkLogDrainContainer();
|
2024-10-14 15:54:29 +00:00
|
|
|
}
|
|
|
|
|
|
2025-09-13 18:32:15 +00:00
|
|
|
private function aggregateMultiContainerStatuses()
|
|
|
|
|
{
|
|
|
|
|
if ($this->applicationContainerStatuses->isEmpty()) {
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
foreach ($this->applicationContainerStatuses as $applicationId => $containerStatuses) {
|
|
|
|
|
$application = $this->applications->where('id', $applicationId)->first();
|
|
|
|
|
if (! $application) {
|
|
|
|
|
continue;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Parse docker compose to check for excluded containers
|
|
|
|
|
$dockerComposeRaw = data_get($application, 'docker_compose_raw');
|
|
|
|
|
$excludedContainers = collect();
|
|
|
|
|
|
|
|
|
|
if ($dockerComposeRaw) {
|
|
|
|
|
try {
|
|
|
|
|
$dockerCompose = \Symfony\Component\Yaml\Yaml::parse($dockerComposeRaw);
|
|
|
|
|
$services = data_get($dockerCompose, 'services', []);
|
|
|
|
|
|
|
|
|
|
foreach ($services as $serviceName => $serviceConfig) {
|
|
|
|
|
// Check if container should be excluded
|
|
|
|
|
$excludeFromHc = data_get($serviceConfig, 'exclude_from_hc', false);
|
|
|
|
|
$restartPolicy = data_get($serviceConfig, 'restart', 'always');
|
|
|
|
|
|
|
|
|
|
if ($excludeFromHc || $restartPolicy === 'no') {
|
|
|
|
|
$excludedContainers->push($serviceName);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
} catch (\Exception $e) {
|
|
|
|
|
// If we can't parse, treat all containers as included
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Filter out excluded containers
|
|
|
|
|
$relevantStatuses = $containerStatuses->filter(function ($status, $containerName) use ($excludedContainers) {
|
|
|
|
|
return ! $excludedContainers->contains($containerName);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
// If all containers are excluded, don't update status
|
|
|
|
|
if ($relevantStatuses->isEmpty()) {
|
|
|
|
|
continue;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Aggregate status: if any container is running, app is running
|
|
|
|
|
$hasRunning = false;
|
|
|
|
|
$hasUnhealthy = false;
|
2025-11-19 12:40:58 +00:00
|
|
|
$hasUnknown = false;
|
2025-09-13 18:32:15 +00:00
|
|
|
|
|
|
|
|
foreach ($relevantStatuses as $status) {
|
|
|
|
|
if (str($status)->contains('running')) {
|
|
|
|
|
$hasRunning = true;
|
|
|
|
|
if (str($status)->contains('unhealthy')) {
|
|
|
|
|
$hasUnhealthy = true;
|
|
|
|
|
}
|
2025-11-19 12:40:58 +00:00
|
|
|
if (str($status)->contains('unknown')) {
|
|
|
|
|
$hasUnknown = true;
|
|
|
|
|
}
|
2025-09-13 18:32:15 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
$aggregatedStatus = null;
|
|
|
|
|
if ($hasRunning) {
|
2025-11-19 12:40:58 +00:00
|
|
|
if ($hasUnhealthy) {
|
|
|
|
|
$aggregatedStatus = 'running (unhealthy)';
|
|
|
|
|
} elseif ($hasUnknown) {
|
|
|
|
|
$aggregatedStatus = 'running (unknown)';
|
|
|
|
|
} else {
|
|
|
|
|
$aggregatedStatus = 'running (healthy)';
|
|
|
|
|
}
|
2025-09-13 18:32:15 +00:00
|
|
|
} else {
|
|
|
|
|
// All containers are exited
|
|
|
|
|
$aggregatedStatus = 'exited (unhealthy)';
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Update application status with aggregated result
|
|
|
|
|
if ($aggregatedStatus && $application->status !== $aggregatedStatus) {
|
debug: add comprehensive status change logging
Added detailed debug logging to all status update paths to help
diagnose why "unhealthy" status appears in the UI.
## Logging Added
### 1. PushServerUpdateJob (Sentinel updates)
**Location**: Lines 303-315
**Logs**: Status changes from Sentinel push updates
**Data tracked**:
- Old vs new status
- Container statuses that led to aggregation
- Status flags (hasRunning, hasUnhealthy, hasUnknown)
### 2. GetContainersStatus (SSH updates)
**Location**: Lines 441-449, 346-354, 358-365
**Logs**: Status changes from SSH-based checks
**Scenarios**:
- Normal status aggregation
- Recently restarted containers (kept as degraded)
- Applications not running (set to exited)
**Data tracked**:
- Old vs new status
- Container statuses
- Restart count and timing
- Whether containers exist
### 3. Application Model Status Accessor
**Location**: Lines 706-712, 726-732
**Logs**: When status is set without explicit health information
**Issue**: Highlights cases where health defaults to "unhealthy"
**Data tracked**:
- Raw value passed to setter
- Final result after default applied
## How to Use
### Enable Debug Logging
Edit `.env` or `config/logging.php` to set log level to debug:
```
LOG_LEVEL=debug
```
### Monitor Logs
```bash
tail -f storage/logs/laravel.log | grep STATUS-DEBUG
```
### Log Format
All logs use `[STATUS-DEBUG]` prefix for easy filtering:
```
[2025-11-19 13:00:00] local.DEBUG: [STATUS-DEBUG] Sentinel status change
{
"source": "PushServerUpdateJob",
"app_id": 123,
"app_name": "my-app",
"old_status": "running:unknown",
"new_status": "running:healthy",
"container_statuses": [...],
"flags": {...}
}
```
## What to Look For
1. **Default to unhealthy**: Check Application model accessor logs
2. **Status flipping**: Compare timestamps between Sentinel and SSH updates
3. **Incorrect aggregation**: Check flags and container_statuses
4. **Stale database values**: Check if old_status persists across multiple logs
## Next Steps
After gathering logs, we can:
1. Identify the exact source of "unhealthy" status
2. Determine if it's a default issue, aggregation bug, or timing problem
3. Apply targeted fix based on evidence
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-19 12:52:08 +00:00
|
|
|
Log::debug('[STATUS-DEBUG] Sentinel status change', [
|
|
|
|
|
'source' => 'PushServerUpdateJob',
|
|
|
|
|
'app_id' => $application->id,
|
|
|
|
|
'app_name' => $application->name,
|
|
|
|
|
'old_status' => $application->status,
|
|
|
|
|
'new_status' => $aggregatedStatus,
|
|
|
|
|
'container_statuses' => $relevantStatuses->toArray(),
|
|
|
|
|
'flags' => [
|
|
|
|
|
'hasRunning' => $hasRunning,
|
|
|
|
|
'hasUnhealthy' => $hasUnhealthy,
|
|
|
|
|
'hasUnknown' => $hasUnknown,
|
|
|
|
|
],
|
|
|
|
|
]);
|
2025-09-13 18:32:15 +00:00
|
|
|
$application->status = $aggregatedStatus;
|
|
|
|
|
$application->save();
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2024-10-14 15:54:29 +00:00
|
|
|
private function updateApplicationStatus(string $applicationId, string $containerStatus)
|
|
|
|
|
{
|
2024-10-14 20:53:16 +00:00
|
|
|
$application = $this->applications->where('id', $applicationId)->first();
|
2024-10-14 15:54:29 +00:00
|
|
|
if (! $application) {
|
|
|
|
|
return;
|
|
|
|
|
}
|
2025-06-06 12:47:54 +00:00
|
|
|
if ($application->status !== $containerStatus) {
|
|
|
|
|
$application->status = $containerStatus;
|
|
|
|
|
$application->save();
|
|
|
|
|
}
|
2024-10-14 15:54:29 +00:00
|
|
|
}
|
|
|
|
|
|
2025-06-04 08:03:36 +00:00
|
|
|
private function updateApplicationPreviewStatus(string $applicationId, string $pullRequestId, string $containerStatus)
|
2024-10-14 15:54:29 +00:00
|
|
|
{
|
2025-06-04 08:03:36 +00:00
|
|
|
$application = $this->previews->where('application_id', $applicationId)
|
|
|
|
|
->where('pull_request_id', $pullRequestId)
|
|
|
|
|
->first();
|
2024-10-14 15:54:29 +00:00
|
|
|
if (! $application) {
|
|
|
|
|
return;
|
2024-10-14 11:32:36 +00:00
|
|
|
}
|
2025-06-04 08:03:36 +00:00
|
|
|
if ($application->status !== $containerStatus) {
|
|
|
|
|
$application->status = $containerStatus;
|
|
|
|
|
$application->save();
|
|
|
|
|
}
|
2024-10-14 15:54:29 +00:00
|
|
|
}
|
2024-10-14 11:32:36 +00:00
|
|
|
|
2024-10-14 15:54:29 +00:00
|
|
|
private function updateNotFoundApplicationStatus()
|
|
|
|
|
{
|
|
|
|
|
$notFoundApplicationIds = $this->allApplicationIds->diff($this->foundApplicationIds);
|
2024-10-14 11:32:36 +00:00
|
|
|
if ($notFoundApplicationIds->isNotEmpty()) {
|
2024-10-14 15:54:29 +00:00
|
|
|
$notFoundApplicationIds->each(function ($applicationId) {
|
|
|
|
|
$application = Application::find($applicationId);
|
|
|
|
|
if ($application) {
|
2025-06-04 08:03:36 +00:00
|
|
|
// Don't mark as exited if already exited
|
|
|
|
|
if (str($application->status)->startsWith('exited')) {
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Only protection: Verify we received any container data at all
|
|
|
|
|
// If containers collection is completely empty, Sentinel might have failed
|
|
|
|
|
if ($this->containers->isEmpty()) {
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
2025-06-06 12:47:54 +00:00
|
|
|
if ($application->status !== 'exited') {
|
|
|
|
|
$application->status = 'exited';
|
|
|
|
|
$application->save();
|
|
|
|
|
}
|
2024-10-14 15:54:29 +00:00
|
|
|
}
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
private function updateNotFoundApplicationPreviewStatus()
|
|
|
|
|
{
|
|
|
|
|
$notFoundApplicationPreviewsIds = $this->allApplicationPreviewsIds->diff($this->foundApplicationPreviewsIds);
|
|
|
|
|
if ($notFoundApplicationPreviewsIds->isNotEmpty()) {
|
2025-06-04 08:03:36 +00:00
|
|
|
$notFoundApplicationPreviewsIds->each(function ($previewKey) {
|
|
|
|
|
// Parse the previewKey format "application_id:pull_request_id"
|
|
|
|
|
$parts = explode(':', $previewKey);
|
|
|
|
|
if (count($parts) !== 2) {
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
$applicationId = $parts[0];
|
|
|
|
|
$pullRequestId = $parts[1];
|
|
|
|
|
|
|
|
|
|
$applicationPreview = $this->previews->where('application_id', $applicationId)
|
|
|
|
|
->where('pull_request_id', $pullRequestId)
|
|
|
|
|
->first();
|
|
|
|
|
|
2024-10-14 15:54:29 +00:00
|
|
|
if ($applicationPreview) {
|
2025-06-04 08:03:36 +00:00
|
|
|
// Don't mark as exited if already exited
|
|
|
|
|
if (str($applicationPreview->status)->startsWith('exited')) {
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Only protection: Verify we received any container data at all
|
|
|
|
|
// If containers collection is completely empty, Sentinel might have failed
|
|
|
|
|
if ($this->containers->isEmpty()) {
|
|
|
|
|
|
|
|
|
|
return;
|
|
|
|
|
}
|
2025-06-06 12:47:54 +00:00
|
|
|
if ($applicationPreview->status !== 'exited') {
|
|
|
|
|
$applicationPreview->status = 'exited';
|
|
|
|
|
$applicationPreview->save();
|
|
|
|
|
}
|
2024-10-14 15:54:29 +00:00
|
|
|
}
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
private function updateProxyStatus()
|
|
|
|
|
{
|
|
|
|
|
// If proxy is not found, start it
|
2024-10-15 11:39:19 +00:00
|
|
|
if ($this->server->isProxyShouldRun()) {
|
|
|
|
|
if ($this->foundProxy === false) {
|
|
|
|
|
try {
|
|
|
|
|
if (CheckProxy::run($this->server)) {
|
2025-06-16 11:13:01 +00:00
|
|
|
StartProxy::run($this->server, async: false);
|
2024-10-22 09:42:24 +00:00
|
|
|
$this->server->team?->notify(new ContainerRestarted('coolify-proxy', $this->server));
|
2024-10-15 11:39:19 +00:00
|
|
|
}
|
|
|
|
|
} catch (\Throwable $e) {
|
|
|
|
|
}
|
|
|
|
|
} else {
|
|
|
|
|
$connectProxyToDockerNetworks = connectProxyToNetworks($this->server);
|
|
|
|
|
instant_remote_process($connectProxyToDockerNetworks, $this->server, false);
|
|
|
|
|
}
|
2024-10-14 10:07:37 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2024-10-14 15:54:29 +00:00
|
|
|
private function updateDatabaseStatus(string $databaseUuid, string $containerStatus, bool $tcpProxy = false)
|
2024-10-14 11:32:36 +00:00
|
|
|
{
|
2024-10-14 20:53:16 +00:00
|
|
|
$database = $this->databases->where('uuid', $databaseUuid)->first();
|
2024-10-14 15:54:29 +00:00
|
|
|
if (! $database) {
|
|
|
|
|
return;
|
|
|
|
|
}
|
2025-06-06 12:47:54 +00:00
|
|
|
if ($database->status !== $containerStatus) {
|
|
|
|
|
$database->status = $containerStatus;
|
|
|
|
|
$database->save();
|
|
|
|
|
}
|
2024-10-14 17:45:03 +00:00
|
|
|
if ($this->isRunning($containerStatus) && $tcpProxy) {
|
2024-10-14 15:54:29 +00:00
|
|
|
$tcpProxyContainerFound = $this->containers->filter(function ($value, $key) use ($databaseUuid) {
|
2024-10-14 16:04:36 +00:00
|
|
|
return data_get($value, 'name') === "$databaseUuid-proxy" && data_get($value, 'state') === 'running';
|
2024-10-14 15:54:29 +00:00
|
|
|
})->first();
|
|
|
|
|
if (! $tcpProxyContainerFound) {
|
|
|
|
|
StartDatabaseProxy::dispatch($database);
|
2024-10-22 09:42:24 +00:00
|
|
|
$this->server->team?->notify(new ContainerRestarted("TCP Proxy for {$database->name}", $this->server));
|
2024-10-14 15:54:29 +00:00
|
|
|
} else {
|
2024-10-14 11:32:36 +00:00
|
|
|
}
|
2024-10-14 15:54:29 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
private function updateNotFoundDatabaseStatus()
|
|
|
|
|
{
|
|
|
|
|
$notFoundDatabaseUuids = $this->allDatabaseUuids->diff($this->foundDatabaseUuids);
|
|
|
|
|
if ($notFoundDatabaseUuids->isNotEmpty()) {
|
|
|
|
|
$notFoundDatabaseUuids->each(function ($databaseUuid) {
|
2024-10-14 20:53:16 +00:00
|
|
|
$database = $this->databases->where('uuid', $databaseUuid)->first();
|
2024-10-14 15:54:29 +00:00
|
|
|
if ($database) {
|
2025-06-06 12:47:54 +00:00
|
|
|
if ($database->status !== 'exited') {
|
|
|
|
|
$database->status = 'exited';
|
|
|
|
|
$database->save();
|
|
|
|
|
}
|
2024-10-14 17:45:03 +00:00
|
|
|
if ($database->is_public) {
|
|
|
|
|
StopDatabaseProxy::dispatch($database);
|
|
|
|
|
}
|
2024-10-14 15:54:29 +00:00
|
|
|
}
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
private function updateServiceSubStatus(string $serviceId, string $subType, string $subId, string $containerStatus)
|
|
|
|
|
{
|
2024-10-14 20:53:16 +00:00
|
|
|
$service = $this->services->where('id', $serviceId)->first();
|
2024-10-14 15:54:29 +00:00
|
|
|
if (! $service) {
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
if ($subType === 'application') {
|
|
|
|
|
$application = $service->applications()->where('id', $subId)->first();
|
2025-05-29 08:47:26 +00:00
|
|
|
if ($application) {
|
2025-06-06 12:47:54 +00:00
|
|
|
if ($application->status !== $containerStatus) {
|
|
|
|
|
$application->status = $containerStatus;
|
|
|
|
|
$application->save();
|
|
|
|
|
}
|
2025-05-29 08:47:26 +00:00
|
|
|
}
|
2024-10-14 15:54:29 +00:00
|
|
|
} elseif ($subType === 'database') {
|
|
|
|
|
$database = $service->databases()->where('id', $subId)->first();
|
2025-05-29 08:47:26 +00:00
|
|
|
if ($database) {
|
2025-06-06 12:47:54 +00:00
|
|
|
if ($database->status !== $containerStatus) {
|
|
|
|
|
$database->status = $containerStatus;
|
|
|
|
|
$database->save();
|
|
|
|
|
}
|
2025-05-29 08:47:26 +00:00
|
|
|
}
|
2024-10-14 11:32:36 +00:00
|
|
|
}
|
|
|
|
|
}
|
2024-10-14 10:07:37 +00:00
|
|
|
|
2024-10-14 15:54:29 +00:00
|
|
|
private function updateNotFoundServiceStatus()
|
2024-10-14 11:32:36 +00:00
|
|
|
{
|
2024-10-14 15:54:29 +00:00
|
|
|
$notFoundServiceApplicationIds = $this->allServiceApplicationIds->diff($this->foundServiceApplicationIds);
|
|
|
|
|
$notFoundServiceDatabaseIds = $this->allServiceDatabaseIds->diff($this->foundServiceDatabaseIds);
|
|
|
|
|
if ($notFoundServiceApplicationIds->isNotEmpty()) {
|
|
|
|
|
$notFoundServiceApplicationIds->each(function ($serviceApplicationId) {
|
|
|
|
|
$application = ServiceApplication::find($serviceApplicationId);
|
|
|
|
|
if ($application) {
|
2025-06-06 12:47:54 +00:00
|
|
|
if ($application->status !== 'exited') {
|
|
|
|
|
$application->status = 'exited';
|
|
|
|
|
$application->save();
|
|
|
|
|
}
|
2024-10-14 15:54:29 +00:00
|
|
|
}
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
if ($notFoundServiceDatabaseIds->isNotEmpty()) {
|
|
|
|
|
$notFoundServiceDatabaseIds->each(function ($serviceDatabaseId) {
|
|
|
|
|
$database = ServiceDatabase::find($serviceDatabaseId);
|
|
|
|
|
if ($database) {
|
2025-06-06 12:47:54 +00:00
|
|
|
if ($database->status !== 'exited') {
|
|
|
|
|
$database->status = 'exited';
|
|
|
|
|
$database->save();
|
|
|
|
|
}
|
2024-10-14 15:54:29 +00:00
|
|
|
}
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
private function updateAdditionalServersStatus()
|
|
|
|
|
{
|
|
|
|
|
$this->allApplicationsWithAdditionalServers->each(function ($application) {
|
|
|
|
|
ComplexStatusCheck::run($application);
|
2024-10-14 11:32:36 +00:00
|
|
|
});
|
|
|
|
|
}
|
2024-10-14 17:45:03 +00:00
|
|
|
|
|
|
|
|
private function isRunning(string $containerStatus)
|
|
|
|
|
{
|
|
|
|
|
return str($containerStatus)->contains('running');
|
|
|
|
|
}
|
2024-10-15 11:39:19 +00:00
|
|
|
|
2024-10-15 15:03:50 +00:00
|
|
|
private function checkLogDrainContainer()
|
|
|
|
|
{
|
2024-10-15 11:39:19 +00:00
|
|
|
if ($this->server->isLogDrainEnabled() && $this->foundLogDrainContainer === false) {
|
2024-11-22 10:16:01 +00:00
|
|
|
StartLogDrain::dispatch($this->server);
|
2024-10-15 11:39:19 +00:00
|
|
|
}
|
|
|
|
|
}
|
2024-10-14 10:07:37 +00:00
|
|
|
}
|