Admin: misc improvements on admin server and workers. EC now works. (#7055)
* initial design * added simulation as tests * reorganized the codebase to move the simulation framework and tests into their own dedicated package * integration test. ec worker task * remove "enhanced" reference * start master, volume servers, filer Current Status ✅ Master: Healthy and running (port 9333) ✅ Filer: Healthy and running (port 8888) ✅ Volume Servers: All 6 servers running (ports 8080-8085) 🔄 Admin/Workers: Will start when dependencies are ready * generate write load * tasks are assigned * admin start wtih grpc port. worker has its own working directory * Update .gitignore * working worker and admin. Task detection is not working yet. * compiles, detection uses volumeSizeLimitMB from master * compiles * worker retries connecting to admin * build and restart * rendering pending tasks * skip task ID column * sticky worker id * test canScheduleTaskNow * worker reconnect to admin * clean up logs * worker register itself first * worker can run ec work and report status but: 1. one volume should not be repeatedly worked on. 2. ec shards needs to be distributed and source data should be deleted. * move ec task logic * listing ec shards * local copy, ec. Need to distribute. * ec is mostly working now * distribution of ec shards needs improvement * need configuration to enable ec * show ec volumes * interval field UI component * rename * integration test with vauuming * garbage percentage threshold * fix warning * display ec shard sizes * fix ec volumes list * Update ui.go * show default values * ensure correct default value * MaintenanceConfig use ConfigField * use schema defined defaults * config * reduce duplication * refactor to use BaseUIProvider * each task register its schema * checkECEncodingCandidate use ecDetector * use vacuumDetector * use volumeSizeLimitMB * remove remove * remove unused * refactor * use new framework * remove v2 reference * refactor * left menu can scroll now * The maintenance manager was not being initialized when no data directory was configured for persistent storage. * saving config * Update task_config_schema_templ.go * enable/disable tasks * protobuf encoded task configurations * fix system settings * use ui component * remove logs * interface{} Reduction * reduce interface{} * reduce interface{} * avoid from/to map * reduce interface{} * refactor * keep it DRY * added logging * debug messages * debug level * debug * show the log caller line * use configured task policy * log level * handle admin heartbeat response * Update worker.go * fix EC rack and dc count * Report task status to admin server * fix task logging, simplify interface checking, use erasure_coding constants * factor in empty volume server during task planning * volume.list adds disk id * track disk id also * fix locking scheduled and manual scanning * add active topology * simplify task detector * ec task completed, but shards are not showing up * implement ec in ec_typed.go * adjust log level * dedup * implementing ec copying shards and only ecx files * use disk id when distributing ec shards 🎯 Planning: ActiveTopology creates DestinationPlan with specific TargetDisk 📦 Task Creation: maintenance_integration.go creates ECDestination with DiskId 🚀 Task Execution: EC task passes DiskId in VolumeEcShardsCopyRequest 💾 Volume Server: Receives disk_id and stores shards on specific disk (vs.store.Locations[req.DiskId]) 📂 File System: EC shards and metadata land in the exact disk directory planned * Delete original volume from all locations * clean up existing shard locations * local encoding and distributing * Update docker/admin_integration/EC-TESTING-README.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * check volume id range * simplify * fix tests * fix types * clean up logs and tests --------- Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Chris Lu
@@ -70,43 +70,51 @@ templ MaintenanceQueue(data *maintenance.MaintenanceQueueData) {
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Simple task queue display -->
|
||||
<div class="row">
|
||||
<!-- Pending Tasks -->
|
||||
<div class="row mb-4">
|
||||
<div class="col-12">
|
||||
<div class="card">
|
||||
<div class="card-header">
|
||||
<h5 class="mb-0">Task Queue</h5>
|
||||
<div class="card-header bg-primary text-white">
|
||||
<h5 class="mb-0">
|
||||
<i class="fas fa-clock me-2"></i>
|
||||
Pending Tasks
|
||||
</h5>
|
||||
</div>
|
||||
<div class="card-body">
|
||||
if len(data.Tasks) == 0 {
|
||||
if data.Stats.PendingTasks == 0 {
|
||||
<div class="text-center text-muted py-4">
|
||||
<i class="fas fa-clipboard-list fa-3x mb-3"></i>
|
||||
<p>No maintenance tasks in queue</p>
|
||||
<small>Tasks will appear here when the system detects maintenance needs</small>
|
||||
<p>No pending maintenance tasks</p>
|
||||
<small>Pending tasks will appear here when the system detects maintenance needs</small>
|
||||
</div>
|
||||
} else {
|
||||
<div class="table-responsive">
|
||||
<table class="table table-hover">
|
||||
<thead>
|
||||
<tr>
|
||||
<th>ID</th>
|
||||
<th>Type</th>
|
||||
<th>Status</th>
|
||||
<th>Priority</th>
|
||||
<th>Volume</th>
|
||||
<th>Server</th>
|
||||
<th>Reason</th>
|
||||
<th>Created</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
for _, task := range data.Tasks {
|
||||
<tr>
|
||||
<td><code>{task.ID[:8]}...</code></td>
|
||||
<td>{string(task.Type)}</td>
|
||||
<td>{string(task.Status)}</td>
|
||||
<td>{fmt.Sprintf("%d", task.VolumeID)}</td>
|
||||
<td>{task.Server}</td>
|
||||
<td>{task.CreatedAt.Format("2006-01-02 15:04")}</td>
|
||||
</tr>
|
||||
if string(task.Status) == "pending" {
|
||||
<tr>
|
||||
<td>
|
||||
@TaskTypeIcon(task.Type)
|
||||
{string(task.Type)}
|
||||
</td>
|
||||
<td>@PriorityBadge(task.Priority)</td>
|
||||
<td>{fmt.Sprintf("%d", task.VolumeID)}</td>
|
||||
<td><small>{task.Server}</small></td>
|
||||
<td><small>{task.Reason}</small></td>
|
||||
<td>{task.CreatedAt.Format("2006-01-02 15:04")}</td>
|
||||
</tr>
|
||||
}
|
||||
}
|
||||
</tbody>
|
||||
</table>
|
||||
@@ -117,36 +125,171 @@ templ MaintenanceQueue(data *maintenance.MaintenanceQueueData) {
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Workers Summary -->
|
||||
<div class="row mt-4">
|
||||
<!-- Active Tasks -->
|
||||
<div class="row mb-4">
|
||||
<div class="col-12">
|
||||
<div class="card">
|
||||
<div class="card-header">
|
||||
<h5 class="mb-0">Active Workers</h5>
|
||||
<div class="card-header bg-warning text-dark">
|
||||
<h5 class="mb-0">
|
||||
<i class="fas fa-running me-2"></i>
|
||||
Active Tasks
|
||||
</h5>
|
||||
</div>
|
||||
<div class="card-body">
|
||||
if len(data.Workers) == 0 {
|
||||
if data.Stats.RunningTasks == 0 {
|
||||
<div class="text-center text-muted py-4">
|
||||
<i class="fas fa-robot fa-3x mb-3"></i>
|
||||
<p>No workers are currently active</p>
|
||||
<small>Start workers using: <code>weed worker -admin=localhost:9333</code></small>
|
||||
<i class="fas fa-tasks fa-3x mb-3"></i>
|
||||
<p>No active maintenance tasks</p>
|
||||
<small>Active tasks will appear here when workers start processing them</small>
|
||||
</div>
|
||||
} else {
|
||||
<div class="row">
|
||||
for _, worker := range data.Workers {
|
||||
<div class="col-md-4 mb-3">
|
||||
<div class="card">
|
||||
<div class="card-body">
|
||||
<h6 class="card-title">{worker.ID}</h6>
|
||||
<p class="card-text">
|
||||
<small class="text-muted">{worker.Address}</small><br/>
|
||||
Status: {worker.Status}<br/>
|
||||
Load: {fmt.Sprintf("%d/%d", worker.CurrentLoad, worker.MaxConcurrent)}
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
}
|
||||
<div class="table-responsive">
|
||||
<table class="table table-hover">
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Type</th>
|
||||
<th>Status</th>
|
||||
<th>Progress</th>
|
||||
<th>Volume</th>
|
||||
<th>Worker</th>
|
||||
<th>Started</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
for _, task := range data.Tasks {
|
||||
if string(task.Status) == "assigned" || string(task.Status) == "in_progress" {
|
||||
<tr>
|
||||
<td>
|
||||
@TaskTypeIcon(task.Type)
|
||||
{string(task.Type)}
|
||||
</td>
|
||||
<td>@StatusBadge(task.Status)</td>
|
||||
<td>@ProgressBar(task.Progress, task.Status)</td>
|
||||
<td>{fmt.Sprintf("%d", task.VolumeID)}</td>
|
||||
<td>
|
||||
if task.WorkerID != "" {
|
||||
<small>{task.WorkerID}</small>
|
||||
} else {
|
||||
<span class="text-muted">-</span>
|
||||
}
|
||||
</td>
|
||||
<td>
|
||||
if task.StartedAt != nil {
|
||||
{task.StartedAt.Format("2006-01-02 15:04")}
|
||||
} else {
|
||||
<span class="text-muted">-</span>
|
||||
}
|
||||
</td>
|
||||
</tr>
|
||||
}
|
||||
}
|
||||
</tbody>
|
||||
</table>
|
||||
</div>
|
||||
}
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Completed Tasks -->
|
||||
<div class="row mb-4">
|
||||
<div class="col-12">
|
||||
<div class="card">
|
||||
<div class="card-header bg-success text-white">
|
||||
<h5 class="mb-0">
|
||||
<i class="fas fa-check-circle me-2"></i>
|
||||
Completed Tasks
|
||||
</h5>
|
||||
</div>
|
||||
<div class="card-body">
|
||||
if data.Stats.CompletedToday == 0 && data.Stats.FailedToday == 0 {
|
||||
<div class="text-center text-muted py-4">
|
||||
<i class="fas fa-check-circle fa-3x mb-3"></i>
|
||||
<p>No completed maintenance tasks today</p>
|
||||
<small>Completed tasks will appear here after workers finish processing them</small>
|
||||
</div>
|
||||
} else {
|
||||
<div class="table-responsive">
|
||||
<table class="table table-hover">
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Type</th>
|
||||
<th>Status</th>
|
||||
<th>Volume</th>
|
||||
<th>Worker</th>
|
||||
<th>Duration</th>
|
||||
<th>Completed</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
for _, task := range data.Tasks {
|
||||
if string(task.Status) == "completed" || string(task.Status) == "failed" || string(task.Status) == "cancelled" {
|
||||
if string(task.Status) == "failed" {
|
||||
<tr class="table-danger">
|
||||
<td>
|
||||
@TaskTypeIcon(task.Type)
|
||||
{string(task.Type)}
|
||||
</td>
|
||||
<td>@StatusBadge(task.Status)</td>
|
||||
<td>{fmt.Sprintf("%d", task.VolumeID)}</td>
|
||||
<td>
|
||||
if task.WorkerID != "" {
|
||||
<small>{task.WorkerID}</small>
|
||||
} else {
|
||||
<span class="text-muted">-</span>
|
||||
}
|
||||
</td>
|
||||
<td>
|
||||
if task.StartedAt != nil && task.CompletedAt != nil {
|
||||
{formatDuration(task.CompletedAt.Sub(*task.StartedAt))}
|
||||
} else {
|
||||
<span class="text-muted">-</span>
|
||||
}
|
||||
</td>
|
||||
<td>
|
||||
if task.CompletedAt != nil {
|
||||
{task.CompletedAt.Format("2006-01-02 15:04")}
|
||||
} else {
|
||||
<span class="text-muted">-</span>
|
||||
}
|
||||
</td>
|
||||
</tr>
|
||||
} else {
|
||||
<tr>
|
||||
<td>
|
||||
@TaskTypeIcon(task.Type)
|
||||
{string(task.Type)}
|
||||
</td>
|
||||
<td>@StatusBadge(task.Status)</td>
|
||||
<td>{fmt.Sprintf("%d", task.VolumeID)}</td>
|
||||
<td>
|
||||
if task.WorkerID != "" {
|
||||
<small>{task.WorkerID}</small>
|
||||
} else {
|
||||
<span class="text-muted">-</span>
|
||||
}
|
||||
</td>
|
||||
<td>
|
||||
if task.StartedAt != nil && task.CompletedAt != nil {
|
||||
{formatDuration(task.CompletedAt.Sub(*task.StartedAt))}
|
||||
} else {
|
||||
<span class="text-muted">-</span>
|
||||
}
|
||||
</td>
|
||||
<td>
|
||||
if task.CompletedAt != nil {
|
||||
{task.CompletedAt.Format("2006-01-02 15:04")}
|
||||
} else {
|
||||
<span class="text-muted">-</span>
|
||||
}
|
||||
</td>
|
||||
</tr>
|
||||
}
|
||||
}
|
||||
}
|
||||
</tbody>
|
||||
</table>
|
||||
</div>
|
||||
}
|
||||
</div>
|
||||
@@ -156,6 +299,9 @@ templ MaintenanceQueue(data *maintenance.MaintenanceQueueData) {
|
||||
</div>
|
||||
|
||||
<script>
|
||||
// Debug output to browser console
|
||||
console.log("DEBUG: Maintenance Queue Template loaded");
|
||||
|
||||
// Auto-refresh every 10 seconds
|
||||
setInterval(function() {
|
||||
if (!document.hidden) {
|
||||
@@ -163,7 +309,8 @@ templ MaintenanceQueue(data *maintenance.MaintenanceQueueData) {
|
||||
}
|
||||
}, 10000);
|
||||
|
||||
function triggerScan() {
|
||||
window.triggerScan = function() {
|
||||
console.log("triggerScan called");
|
||||
fetch('/api/maintenance/scan', {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
@@ -182,7 +329,12 @@ templ MaintenanceQueue(data *maintenance.MaintenanceQueueData) {
|
||||
.catch(error => {
|
||||
alert('Error: ' + error.message);
|
||||
});
|
||||
}
|
||||
};
|
||||
|
||||
window.refreshPage = function() {
|
||||
console.log("refreshPage called");
|
||||
window.location.reload();
|
||||
};
|
||||
</script>
|
||||
}
|
||||
|
||||
@@ -243,32 +395,13 @@ templ ProgressBar(progress float64, status maintenance.MaintenanceTaskStatus) {
|
||||
}
|
||||
}
|
||||
|
||||
templ WorkerStatusBadge(status string) {
|
||||
switch status {
|
||||
case "active":
|
||||
<span class="badge bg-success">Active</span>
|
||||
case "busy":
|
||||
<span class="badge bg-warning">Busy</span>
|
||||
case "inactive":
|
||||
<span class="badge bg-secondary">Inactive</span>
|
||||
default:
|
||||
<span class="badge bg-light text-dark">Unknown</span>
|
||||
}
|
||||
}
|
||||
|
||||
// Helper functions (would be defined in Go)
|
||||
|
||||
|
||||
func getWorkerStatusColor(status string) string {
|
||||
switch status {
|
||||
case "active":
|
||||
return "success"
|
||||
case "busy":
|
||||
return "warning"
|
||||
case "inactive":
|
||||
return "secondary"
|
||||
default:
|
||||
return "light"
|
||||
func formatDuration(d time.Duration) string {
|
||||
if d < time.Minute {
|
||||
return fmt.Sprintf("%.0fs", d.Seconds())
|
||||
} else if d < time.Hour {
|
||||
return fmt.Sprintf("%.1fm", d.Minutes())
|
||||
} else {
|
||||
return fmt.Sprintf("%.1fh", d.Hours())
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user