fix: EventBus panic on SSE disconnect + JWT secret persistence + recover() guards

- eventbus.go: Fix send-on-closed-channel panic in SubscribeGlobal by
  using a done channel; add recover() in fan-out goroutine; track active
  global subs for proper cleanup on unsubscribe
- config.go: Persist JWT secret to $DATA_DIR/.jwt_secret instead of
  regenerating a random one on every restart (which invalidated all sessions)
- handlers_ws.go: Replace time.After with time.Ticker to fix timer leak in
  SSE keepalive loop
- handlers_jobs.go: Add recover() in fire-and-forget job goroutine; fix nil
  pointer deref when GetByID fails after job creation
- handlers_machines.go: Add recover() in ProbeAllMachines goroutine
- scheduler.go: Add recover() in scheduled job run goroutine
- engine.go: Add recover() in per-machine probe goroutines
This commit is contained in:
2026-07-08 22:38:56 -04:00
parent 1798fc6804
commit 58e7f51ba7
7 changed files with 89 additions and 20 deletions
+6 -1
View File
@@ -368,7 +368,12 @@ func (e *Engine) ProbeAllMachines() {
sem <- struct{}{}
go func(m *models.Machine) {
defer wg.Done()
defer func() { <-sem }()
defer func() {
if r := recover(); r != nil {
slog.Error("probe goroutine panicked", "machine_id", m.ID, "panic", r)
}
<-sem
}()
ctx, cancel := context.WithTimeout(context.Background(), probeTimeout)
defer cancel()
+37 -8
View File
@@ -10,6 +10,12 @@ type EventBus struct {
mu sync.RWMutex
global chan Event
bufferSize int
globalSubs []globalSub
}
type globalSub struct {
ch chan Event
done chan struct{}
}
func NewEventBus(bufferSize int) *EventBus {
@@ -17,6 +23,7 @@ func NewEventBus(bufferSize int) *EventBus {
subscribers: make(map[int64]map[chan Event]struct{}),
global: make(chan Event, bufferSize),
bufferSize: bufferSize,
globalSubs: nil,
}
}
@@ -43,20 +50,42 @@ func (eb *EventBus) Subscribe(jobID int64) (chan Event, func()) {
}
func (eb *EventBus) SubscribeGlobal() (chan Event, func()) {
eb.mu.RLock()
ch := make(chan Event, eb.bufferSize)
eb.mu.RUnlock()
done := make(chan struct{})
eb.mu.Lock()
eb.globalSubs = append(eb.globalSubs, globalSub{ch: ch, done: done})
eb.mu.Unlock()
go func() {
for evt := range eb.global {
defer func() {
if r := recover(); r != nil {
slog.Error("SubscribeGlobal goroutine panicked", "reason", r)
}
close(ch)
}()
for {
select {
case ch <- evt:
default:
slog.Warn("global event subscriber buffer full, dropping event", "type", evt.Type)
case evt := <-eb.global:
select {
case ch <- evt:
default:
slog.Warn("global event subscriber buffer full, dropping event", "type", evt.Type)
}
case <-done:
return
}
}
close(ch)
}()
return ch, func() { close(ch) }
return ch, func() {
close(done)
eb.mu.Lock()
for i, s := range eb.globalSubs {
if s.ch == ch {
eb.globalSubs = append(eb.globalSubs[:i], eb.globalSubs[i+1:]...)
break
}
}
eb.mu.Unlock()
}
}
func (eb *EventBus) Publish(evt Event) {