scheduler: recover from panic (#12009)

If processing a specific evaluation causes the scheduler (and
therefore the entire server) to panic, that evaluation will never
get a chance to be nack'd and cleared from the state store. It will
get dequeued by another scheduler, causing that server to panic, and
so forth until all servers are in a panic loop. This prevents the
operator from intervening to remove the evaluation or update the
state.

Recover the goroutine from the top-level `Process` methods for each
scheduler so that this condition can be detected without panicking the
server process. This will lead to a loop of recovering the scheduler
goroutine until the eval can be removed or nack'd, but that's much
better than taking a downtime.

Author: tgross

.changelog/12009.txt

@@ -0,0 +1,3 @@
+```release-note:improvement
+scheduler: recover scheduler goroutines on panic
+```

scheduler/generic_sched.go

@@ -125,7 +125,14 @@ func NewBatchScheduler(logger log.Logger, eventsCh chan<- interface{}, state Sta
 }
 
 // Process is used to handle a single evaluation
-func (s *GenericScheduler) Process(eval *structs.Evaluation) error {
+func (s *GenericScheduler) Process(eval *structs.Evaluation) (err error) {
+
+	defer func() {
+		if r := recover(); r != nil {
+			err = fmt.Errorf("processing eval %q panicked scheduler - please report this as a bug! - %v", eval.ID, r)
+		}
+	}()
+
 	// Store the evaluation
 	s.eval = eval
 

scheduler/scheduler_system.go

@@ -72,7 +72,13 @@ func NewSysBatchScheduler(logger log.Logger, eventsCh chan<- interface{}, state
 }
 
 // Process is used to handle a single evaluation.
-func (s *SystemScheduler) Process(eval *structs.Evaluation) error {
+func (s *SystemScheduler) Process(eval *structs.Evaluation) (err error) {
+
+	defer func() {
+		if r := recover(); r != nil {
+			err = fmt.Errorf("processing eval %q panicked scheduler - please report this as a bug! - %v", eval.ID, r)
+		}
+	}()
 
 	// Store the evaluation
 	s.eval = eval