Add EventBroadcaster metrics for observability and debugging
All checks were successful
CI / build (pull_request) Successful in 38s

Implement comprehensive metrics tracking for EventBroadcaster implementations:

- Add BroadcasterMetrics interface for reading metrics per namespace
- Add MetricsCollector interface and DefaultMetricsCollector implementation
- Track events_published and events_received counters per namespace
- Track active_subscriptions gauge per namespace
- Track publish_errors, subscribe_errors, and dropped_events counters
- Add MetricsProvider interface for EventBroadcaster implementations
- Integrate metrics tracking into EventBus and NATSEventBus
- Add optional Prometheus integration via PrometheusMetricsAdapter

Closes #22

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
2026-01-10 19:23:00 +01:00
parent f0f8978079
commit 71c6011f49
7 changed files with 781 additions and 11 deletions

View File

@@ -66,6 +66,8 @@ func (neb *NATSEventBus) Subscribe(namespaceID string) <-chan *Event {
})
if err != nil {
log.Printf("[NATSEventBus] Failed to subscribe to NATS subject %s: %v", subject, err)
// Record subscription error
neb.metrics.RecordSubscribeError(namespaceID)
} else {
neb.subscriptions = append(neb.subscriptions, sub)
log.Printf("[NATSEventBus] Node %s subscribed to %s", neb.nodeID, subject)
@@ -109,13 +111,16 @@ func (neb *NATSEventBus) handleNATSEvent(msg *nats.Msg) {
return
}
// Record receive from NATS (cross-node event)
neb.metrics.RecordReceive(eventMsg.NamespaceID)
// Forward to local EventBus subscribers
neb.EventBus.Publish(eventMsg.NamespaceID, eventMsg.Event)
}
// Publish publishes an event both locally and to NATS for cross-node broadcasting
func (neb *NATSEventBus) Publish(namespaceID string, event *Event) {
// First publish locally
// First publish locally (this also records metrics)
neb.EventBus.Publish(namespaceID, event)
// Then publish to NATS for other nodes
@@ -130,11 +135,13 @@ func (neb *NATSEventBus) Publish(namespaceID string, event *Event) {
data, err := json.Marshal(eventMsg)
if err != nil {
log.Printf("[NATSEventBus] Failed to marshal event for NATS: %v", err)
neb.metrics.RecordPublishError(namespaceID)
return
}
if err := neb.nc.Publish(subject, data); err != nil {
log.Printf("[NATSEventBus] Failed to publish event to NATS: %v", err)
neb.metrics.RecordPublishError(namespaceID)
return
}
}