feat: worker diagnostics in settings panel

Adds /api/v1/library/maintenance/worker-status (Celery inspect + queue
depths + recent failed photos) and a Workers section in the Settings
dialog so users can debug stuck queues and task failures without
tailing container logs. Auto-polls every 5s while open.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
root
2026-04-09 10:11:33 +02:00
parent 9ed577f40c
commit 42250aa16e
3 changed files with 460 additions and 3 deletions

View File

@@ -252,6 +252,144 @@ async def regenerate_thumbnails(
} }
@router.get("/maintenance/worker-status")
async def get_worker_status(db: AsyncSession = Depends(get_db)):
"""Diagnostics for the Celery worker fleet + recent task failures.
Surfaced in the Settings panel so the user can spot a stuck queue or
a worker that's gone away without tailing container logs. Returns:
- workers: list of {name, status, active, concurrency, queues}
derived from celery_app.control.inspect(). `status` is 'online'
when ping succeeds, 'unreachable' otherwise. Empty list means no
workers are responding at all (broker down, container crashed,
wrong queue routing, etc.).
- queues: per-queue depth read from Redis (LLEN of each queue key
used by celery.kombu). Mirrors what tasks are waiting to be
picked up.
- failures: aggregate count of photos with processing_status='failed'
plus the most recent N error messages so the user can see *why*
things failed without opening the DB.
- broker_ok: bool — could we even reach Redis?
"""
from app.tasks.celery import celery_app
from app.config import settings
import redis as _redis
# ----- Celery inspect (workers + active tasks) -------------------------
workers: list[dict] = []
inspect_error: Optional[str] = None
try:
inspect = celery_app.control.inspect(timeout=1.0)
ping = inspect.ping() or {}
active = inspect.active() or {}
reserved = inspect.reserved() or {}
scheduled = inspect.scheduled() or {}
stats = inspect.stats() or {}
active_queues = inspect.active_queues() or {}
worker_names = set(ping) | set(active) | set(stats)
for name in sorted(worker_names):
wstats = stats.get(name) or {}
pool = wstats.get('pool') or {}
workers.append({
"name": name,
"status": "online" if name in ping else "unreachable",
"active": len(active.get(name, []) or []),
"reserved": len(reserved.get(name, []) or []),
"scheduled": len(scheduled.get(name, []) or []),
"concurrency": pool.get('max-concurrency'),
"processed": (wstats.get('total') or {}),
"queues": [q.get('name') for q in (active_queues.get(name) or [])],
"active_tasks": [
{
"id": t.get('id'),
"name": t.get('name'),
"args": t.get('args'),
"time_start": t.get('time_start'),
}
for t in (active.get(name) or [])[:10]
],
})
except Exception as e:
inspect_error = str(e)
logger.warning(f"Celery inspect failed: {e}")
# ----- Broker / queue depth --------------------------------------------
broker_ok = False
queue_depths: dict[str, int] = {}
broker_error: Optional[str] = None
try:
r = _redis.Redis.from_url(settings.redis_url, socket_timeout=1.0)
r.ping()
broker_ok = True
for q in ('default', 'high', 'low'):
try:
queue_depths[q] = int(r.llen(q) or 0)
except Exception:
queue_depths[q] = 0
except Exception as e:
broker_error = str(e)
logger.warning(f"Redis broker unreachable: {e}")
# ----- Recent task failures from the photos table ----------------------
failed_total = (
await db.execute(
select(func.count(Photo.id)).where(Photo.processing_status == 'failed')
)
).scalar() or 0
recent_failed_rows = (
await db.execute(
select(
Photo.id,
Photo.filename,
Photo.media_type,
Photo.processing_error,
Photo.updated_at,
)
.where(Photo.processing_status == 'failed')
.order_by(Photo.updated_at.desc().nullslast())
.limit(20)
)
).all()
recent_failures = [
{
"photo_id": row[0],
"filename": row[1],
"media_type": row[2],
"error": (row[3] or '')[:500],
"updated_at": row[4].isoformat() if row[4] else None,
}
for row in recent_failed_rows
]
# ----- Most recent scan errors (Redis list) ----------------------------
scan_errors: list[str] = []
try:
if broker_ok:
r = _redis.Redis.from_url(settings.redis_url, socket_timeout=1.0)
raw = r.lrange('scan:errors', 0, 19) or []
scan_errors = [e.decode(errors='replace') for e in raw]
except Exception as e:
logger.debug(f"Could not read scan:errors: {e}")
return {
"broker_ok": broker_ok,
"broker_error": broker_error,
"inspect_error": inspect_error,
"workers": workers,
"worker_count": len(workers),
"queues": queue_depths,
"failures": {
"total": failed_total,
"recent": recent_failures,
},
"scan_errors": scan_errors,
}
@router.post("/maintenance/cleanup") @router.post("/maintenance/cleanup")
async def run_data_integrity_cleanup(): async def run_data_integrity_cleanup():
"""Re-run the source-roots / folders / photos data-integrity cleanup """Re-run the source-roots / folders / photos data-integrity cleanup

View File

@@ -8,6 +8,9 @@ import {
AlertTriangle, AlertTriangle,
Database, Database,
Loader2, Loader2,
Cpu,
AlertCircle,
CheckCircle2,
} from 'lucide-react' } from 'lucide-react'
import clsx from 'clsx' import clsx from 'clsx'
import { import {
@@ -15,6 +18,7 @@ import {
type ThumbnailStats, type ThumbnailStats,
type LibraryStats, type LibraryStats,
type MediaType, type MediaType,
type WorkerStatus,
} from '../../services/api' } from '../../services/api'
import { toast } from '../ToastContainer' import { toast } from '../ToastContainer'
@@ -37,7 +41,10 @@ interface SettingsDialogProps {
export function SettingsDialog({ isOpen, onClose }: SettingsDialogProps) { export function SettingsDialog({ isOpen, onClose }: SettingsDialogProps) {
const [thumbStats, setThumbStats] = useState<ThumbnailStats | null>(null) const [thumbStats, setThumbStats] = useState<ThumbnailStats | null>(null)
const [libStats, setLibStats] = useState<LibraryStats | null>(null) const [libStats, setLibStats] = useState<LibraryStats | null>(null)
const [workerStatus, setWorkerStatus] = useState<WorkerStatus | null>(null)
const [loadingStats, setLoadingStats] = useState(false) const [loadingStats, setLoadingStats] = useState(false)
const [loadingWorkers, setLoadingWorkers] = useState(false)
const [showAllErrors, setShowAllErrors] = useState(false)
// One key per action so each button has its own spinner without // One key per action so each button has its own spinner without
// blocking the others. // blocking the others.
const [busy, setBusy] = useState<Record<string, boolean>>({}) const [busy, setBusy] = useState<Record<string, boolean>>({})
@@ -59,16 +66,38 @@ export function SettingsDialog({ isOpen, onClose }: SettingsDialogProps) {
} }
}, []) }, [])
// Esc closes; load stats when opened. const refreshWorkers = useCallback(async () => {
setLoadingWorkers(true)
try {
const ws = await library.maintenance.workerStatus()
setWorkerStatus(ws)
} catch (e) {
console.error('Failed to load worker status', e)
toast.error('Could not load worker status')
} finally {
setLoadingWorkers(false)
}
}, [])
// Esc closes; load stats when opened. Workers section auto-polls
// every 5s while the dialog is open so the user sees live worker
// activity without manually hammering the refresh button.
useEffect(() => { useEffect(() => {
if (!isOpen) return if (!isOpen) return
refreshStats() refreshStats()
refreshWorkers()
const handler = (e: KeyboardEvent) => { const handler = (e: KeyboardEvent) => {
if (e.key === 'Escape') onClose() if (e.key === 'Escape') onClose()
} }
window.addEventListener('keydown', handler) window.addEventListener('keydown', handler)
return () => window.removeEventListener('keydown', handler) const poll = window.setInterval(() => {
}, [isOpen, onClose, refreshStats]) refreshWorkers()
}, 5000)
return () => {
window.removeEventListener('keydown', handler)
window.clearInterval(poll)
}
}, [isOpen, onClose, refreshStats, refreshWorkers])
const runAction = useCallback( const runAction = useCallback(
async <T,>( async <T,>(
@@ -254,6 +283,235 @@ export function SettingsDialog({ isOpen, onClose }: SettingsDialogProps) {
</div> </div>
</Section> </Section>
{/* ----------------------------------------------------- */}
{/* Worker fleet diagnostics */}
{/* ----------------------------------------------------- */}
<Section
icon={<Cpu className="h-4 w-4" />}
title="Workers"
right={
<button
onClick={refreshWorkers}
disabled={loadingWorkers}
className="flex items-center gap-1 rounded border border-border px-2 py-1 text-xs text-text-muted hover:bg-surface-2 disabled:opacity-50"
>
{loadingWorkers ? (
<Loader2 className="h-3 w-3 animate-spin" />
) : (
<RefreshCw className="h-3 w-3" />
)}
Refresh
</button>
}
>
{/* Top-line health */}
<div className="grid grid-cols-3 gap-2 text-xs">
<Stat
label="Workers"
value={workerStatus?.worker_count}
tone={
workerStatus
? workerStatus.worker_count > 0
? 'ok'
: 'warn'
: 'muted'
}
/>
<Stat
label="Broker"
value={
workerStatus
? workerStatus.broker_ok
? 'OK'
: 'DOWN'
: undefined
}
tone={
workerStatus
? workerStatus.broker_ok
? 'ok'
: 'warn'
: 'muted'
}
/>
<Stat
label="Failed tasks"
value={workerStatus?.failures.total}
tone={
workerStatus && workerStatus.failures.total > 0
? 'warn'
: 'muted'
}
/>
</div>
{/* Inline error banners for the obvious failure modes */}
{workerStatus?.broker_error && (
<ErrorBanner
title="Cannot reach Redis broker"
detail={workerStatus.broker_error}
/>
)}
{workerStatus?.inspect_error && (
<ErrorBanner
title="Celery inspect failed"
detail={workerStatus.inspect_error}
/>
)}
{workerStatus &&
workerStatus.broker_ok &&
workerStatus.worker_count === 0 && (
<ErrorBanner
title="No workers responding"
detail="Broker is reachable but no celery worker pinged back. Check the mulita-worker container logs."
/>
)}
{/* Queue depth */}
{workerStatus && (
<div className="mt-3">
<div className="mb-1 text-[10px] uppercase tracking-wide text-text-muted">
Queue depth
</div>
<div className="grid grid-cols-3 gap-2 text-xs">
{Object.entries(workerStatus.queues).map(([name, depth]) => (
<div
key={name}
className="flex items-center justify-between rounded bg-surface px-2 py-1"
>
<span className="text-text-muted">{name}</span>
<span
className={clsx(
'font-mono font-semibold',
depth > 0 ? 'text-text' : 'text-text-muted'
)}
>
{depth}
</span>
</div>
))}
</div>
</div>
)}
{/* Per-worker breakdown */}
{workerStatus && workerStatus.workers.length > 0 && (
<div className="mt-3 space-y-2">
<div className="text-[10px] uppercase tracking-wide text-text-muted">
Worker fleet
</div>
{workerStatus.workers.map((w) => (
<div
key={w.name}
className="rounded border border-border bg-surface p-2 text-xs"
>
<div className="flex items-center justify-between">
<div className="flex items-center gap-2">
{w.status === 'online' ? (
<CheckCircle2 className="h-3.5 w-3.5 text-pick" />
) : (
<AlertCircle className="h-3.5 w-3.5 text-reject" />
)}
<span className="font-mono text-text">{w.name}</span>
</div>
<span className="text-text-muted">
{w.active}/{w.concurrency ?? '?'} active
</span>
</div>
<div className="mt-1 flex flex-wrap gap-x-3 gap-y-0.5 text-[10px] text-text-muted">
<span>reserved: {w.reserved}</span>
<span>scheduled: {w.scheduled}</span>
{w.queues.length > 0 && (
<span>queues: {w.queues.join(', ')}</span>
)}
</div>
{w.active_tasks.length > 0 && (
<div className="mt-1.5 space-y-0.5 border-t border-border pt-1.5">
{w.active_tasks.map((t) => (
<div
key={t.id}
className="truncate font-mono text-[10px] text-text-muted"
title={`${t.name} ${JSON.stringify(t.args)}`}
>
<span className="text-text">{t.name}</span>{' '}
{Array.isArray(t.args)
? t.args.map((a) => String(a)).join(', ')
: ''}
</div>
))}
</div>
)}
</div>
))}
</div>
)}
{/* Recent task failures */}
{workerStatus && workerStatus.failures.recent.length > 0 && (
<div className="mt-3">
<div className="mb-1 flex items-center justify-between">
<div className="text-[10px] uppercase tracking-wide text-text-muted">
Recent failures ({workerStatus.failures.total})
</div>
{workerStatus.failures.recent.length > 5 && (
<button
onClick={() => setShowAllErrors((v) => !v)}
className="text-[10px] text-text-muted hover:text-text"
>
{showAllErrors ? 'Show less' : 'Show all'}
</button>
)}
</div>
<div className="max-h-48 space-y-1 overflow-y-auto rounded border border-border bg-surface p-2">
{(showAllErrors
? workerStatus.failures.recent
: workerStatus.failures.recent.slice(0, 5)
).map((f) => (
<div
key={f.photo_id}
className="border-b border-border/40 pb-1 last:border-b-0 last:pb-0"
>
<div className="flex items-center justify-between gap-2 text-[11px]">
<span className="truncate font-mono text-text">
{f.filename}
</span>
<span className="shrink-0 text-[10px] text-text-muted">
{f.media_type}
</span>
</div>
<div className="break-all font-mono text-[10px] text-reject">
{f.error || '(no error message)'}
</div>
</div>
))}
</div>
</div>
)}
{/* Recent scan errors (Redis list) */}
{workerStatus && workerStatus.scan_errors.length > 0 && (
<div className="mt-3">
<div className="mb-1 text-[10px] uppercase tracking-wide text-text-muted">
Scan errors
</div>
<div className="max-h-32 space-y-0.5 overflow-y-auto rounded border border-border bg-surface p-2 font-mono text-[10px] text-reject">
{workerStatus.scan_errors.map((e, i) => (
<div key={i} className="break-all">
{e}
</div>
))}
</div>
</div>
)}
{!workerStatus && (
<div className="mt-3 flex items-center gap-2 text-xs text-text-muted">
<Loader2 className="h-3 w-3 animate-spin" />
Loading worker status
</div>
)}
</Section>
{/* ----------------------------------------------------- */} {/* ----------------------------------------------------- */}
{/* Data integrity */} {/* Data integrity */}
{/* ----------------------------------------------------- */} {/* ----------------------------------------------------- */}
@@ -345,6 +603,20 @@ function Stat({
) )
} }
function ErrorBanner({ title, detail }: { title: string; detail: string }) {
return (
<div className="mt-3 rounded border border-reject/40 bg-reject/10 p-2 text-xs">
<div className="flex items-center gap-1.5 font-medium text-reject">
<AlertTriangle className="h-3.5 w-3.5" />
{title}
</div>
<div className="mt-0.5 break-all font-mono text-[10px] text-reject/80">
{detail}
</div>
</div>
)
}
function ActionButton({ function ActionButton({
loading, loading,
disabled, disabled,

View File

@@ -230,6 +230,45 @@ export interface RegenerateResult {
} }
} }
export interface WorkerInfo {
name: string
status: 'online' | 'unreachable'
active: number
reserved: number
scheduled: number
concurrency: number | null
processed: Record<string, number>
queues: string[]
active_tasks: Array<{
id: string
name: string
args: unknown
time_start: number | null
}>
}
export interface WorkerFailure {
photo_id: string
filename: string
media_type: string
error: string
updated_at: string | null
}
export interface WorkerStatus {
broker_ok: boolean
broker_error: string | null
inspect_error: string | null
workers: WorkerInfo[]
worker_count: number
queues: Record<string, number>
failures: {
total: number
recent: WorkerFailure[]
}
scan_errors: string[]
}
export const library = { export const library = {
scan: async () => { scan: async () => {
const response = await api.post('/library/scan') const response = await api.post('/library/scan')
@@ -265,6 +304,14 @@ export const library = {
return response.data return response.data
}, },
/** Celery worker fleet diagnostics + recent task failures. Surfaced
* in the Settings panel so users can debug stuck queues without
* tailing container logs. */
workerStatus: async (): Promise<WorkerStatus> => {
const response = await api.get('/library/maintenance/worker-status')
return response.data
},
/** Re-run the source-roots / folders / photos integrity cleanup that /** Re-run the source-roots / folders / photos integrity cleanup that
* normally runs on backend startup. */ * normally runs on backend startup. */
cleanup: async (): Promise<{ status: string; message?: string }> => { cleanup: async (): Promise<{ status: string; message?: string }> => {